DS3003 Introduction to R
Youmi Suk
8/24/2021
1. R as a Simple Calculator
Simple calculation
1 + 1 #(for mac, command + enter)[1] 2sqrt(36) / 3 + 2 * .5 # 2 + 1[1] 3sqrt(36)/3+2*.5[1] 3sqrt(36) / (3 + 2 * .5) # some calculations. [1] 1.5?sqrtAssigning values to an R object
x <- sqrt(36) / 3 + 2 * .5 # you can also use "=" instead of "<-"
x # print content of R object "x" on the screen[1] 3Simple computations with “x”
7*x[1] 21y <- 7*x
y[1] 21y/x[1] 7Important shortcuts and advice
use Ctrl+R (Windows) or Command+Enter (Mac) to run a selection or a single line
everything after a pound sign (#) is a commentary
(i.e., R does not try to interpret numbers and character strings that follow a pound sign)
always try to carefully comment your R-script/R-markdown files
develop a clear style in writing R-script/R-markdown files
guidelines for a clear style can be found at https://google.github.io/styleguide/Rguide.xml
basic terminology for functions:
function(arg1, arg2, arg3, ...) e.g. sqrt(x = 36)
| | | | | | |
function name arguments function name / argument name / argument value
"sqrt" "x" "36"
Help
?sqrt # see help for sqrt()2. Set Working Directory
- You need specify the corresponding path on your computer
setwd('/Users/youmisuk/Box/DS3003/W1 - Syllabus & R intro') # working directory on my laptop3. Reading Data
Read tabulator separated data
incex <- read.table('income_exmpl.dat', header = T, sep = "\t")
head(incex) # print the first 6 lines on the screen sex age edu occ oexp income
1 f 62 low low 35 953
2 m 32 high high 6 1224
3 m 56 med. high 36 1466
4 f 63 med. med. 38 1339
5 m 20 low low 3 1184
6 f 38 med. med. 12 1196# if the data are not located in the working directory (see setwd()) then you
# can read the data by specifying the full path
incex <- read.table('/Users/youmisuk/Box/DS3003/W1 - Syllabus & R intro/income_exmpl.dat',
header = T, sep = "\t")
# if an R function requires a character string or name as an argument (e.g., the file name
# or path), it must be set in quotes ("name" or 'name')Read comma separated data
?read.csv # help on reading CSV data
incex.2 <- read.csv('income_exmpl.csv')Read other data formats (e.g., SPSS, SAS, or STATA)
- use the ‘foreign’-package
- install package from server, for example, in Berkeley
- alternatively use menu bar,
Tools
#install.packages('foreign', repos = 'http://cran.cnr.Berkeley.edu/')
library(foreign) # load package (makes its functions available)
#library(help = 'foreign') # help on the package
#?read.spss # help on reading SPSS data files (.sav)
incex.3 <- read.spss('income_exmpl.sav', to.data.frame = TRUE)Advice
- If you want to understand an R function you need to carefully read the help file.
- This saves you from getting cryptic error messages and becoming increasingly frustrated.
- In particular, look at the default setting of the arguments, e.g. for to.data.frame
4. Generic Functions
Simple description of data structure
# incex # prints the data on the screen = print(incex)
head(incex, 10) # returns the first six lines of the data frame sex age edu occ oexp income
1 f 62 low low 35 953
2 m 32 high high 6 1224
3 m 56 med. high 36 1466
4 f 63 med. med. 38 1339
5 m 20 low low 3 1184
6 f 38 med. med. 12 1196
7 f 39 med. low 13 951
8 f 53 low low 30 1039
9 m 49 low med. 31 1438
10 f 54 low low 30 1000tail(incex) # returns the last six lines of the data frame sex age edu occ oexp income
1922 m 28 low med. 11 1256
1923 m 25 low low 8 1429
1924 f 33 high high 5 1659
1925 f 35 med. med. 12 1141
1926 f 59 med. high 34 1399
1927 m 57 low high 39 1370incex[1:10, ] # returns the first ten lines by subscripting: incex[rows, cols] sex age edu occ oexp income
1 f 62 low low 35 953
2 m 32 high high 6 1224
3 m 56 med. high 36 1466
4 f 63 med. med. 38 1339
5 m 20 low low 3 1184
6 f 38 med. med. 12 1196
7 f 39 med. low 13 951
8 f 53 low low 30 1039
9 m 49 low med. 31 1438
10 f 54 low low 30 1000str(incex) # shows the structure of the data frame'data.frame': 1922 obs. of 6 variables:
$ sex : chr "f" "m" "m" "f" ...
$ age : int 62 32 56 63 20 38 39 53 49 54 ...
$ edu : chr "low" "high" "med." "med." ...
$ occ : chr "low" "high" "high" "med." ...
$ oexp : int 35 6 36 38 3 12 13 30 31 30 ...
$ income: int 953 1224 1466 1339 1184 1196 951 1039 1438 1000 ...dim(incex) # dimension of data (rows and colums)[1] 1922 6nrow(incex) # number of rows[1] 1922ncol(incex) # number of columns[1] 6names(incex) # variable names of the data frame[1] "sex" "age" "edu" "occ" "oexp" "income"dimnames(incex) # list of row & variable names of the data frame[[1]]
[1] "1" "2" "3" "4" "5" "6" "7" "8" "9" "10"
[11] "11" "12" "13" "14" "15" "16" "17" "18" "19" "20"
[21] "21" "22" "23" "24" "25" "26" "27" "28" "29" "30"
[31] "31" "32" "33" "34" "35" "36" "37" "38" "39" "40"
[41] "41" "42" "43" "44" "45" "46" "47" "48" "49" "50"
[51] "51" "52" "53" "54" "55" "56" "57" "58" "59" "60"
[61] "61" "62" "63" "64" "65" "66" "67" "68" "69" "70"
[71] "71" "72" "73" "74" "75" "76" "77" "78" "79" "80"
[81] "81" "82" "83" "84" "85" "86" "87" "88" "89" "90"
[91] "91" "92" "93" "94" "95" "96" "97" "98" "99" "100"
[101] "101" "102" "103" "104" "105" "106" "107" "108" "109" "110"
[111] "111" "112" "113" "114" "115" "116" "117" "118" "119" "120"
[121] "121" "122" "123" "124" "125" "126" "127" "128" "129" "130"
[131] "131" "132" "133" "134" "135" "136" "137" "138" "139" "140"
[141] "141" "142" "143" "144" "145" "146" "147" "148" "149" "150"
[151] "151" "152" "153" "154" "155" "156" "157" "158" "159" "160"
[161] "161" "162" "163" "164" "165" "166" "167" "168" "169" "170"
[171] "171" "172" "173" "174" "175" "176" "177" "178" "179" "180"
[181] "181" "182" "183" "184" "185" "186" "187" "188" "189" "190"
[191] "191" "192" "193" "194" "195" "196" "197" "198" "199" "200"
[201] "201" "202" "203" "204" "205" "206" "207" "208" "209" "210"
[211] "211" "212" "213" "214" "215" "216" "217" "218" "219" "220"
[221] "221" "222" "223" "224" "225" "226" "227" "228" "229" "230"
[231] "231" "232" "233" "234" "235" "236" "237" "238" "239" "240"
[241] "241" "242" "243" "244" "245" "246" "247" "248" "249" "250"
[251] "251" "252" "253" "254" "255" "256" "257" "258" "259" "260"
[261] "261" "262" "263" "264" "265" "266" "267" "268" "269" "270"
[271] "271" "272" "273" "274" "275" "276" "277" "278" "279" "280"
[281] "281" "283" "284" "285" "286" "287" "288" "289" "290" "291"
[291] "292" "293" "294" "295" "296" "297" "298" "299" "300" "301"
[301] "302" "303" "304" "305" "306" "307" "308" "309" "310" "311"
[311] "312" "313" "314" "315" "316" "317" "318" "319" "320" "321"
[321] "322" "323" "324" "325" "326" "327" "328" "329" "330" "331"
[331] "332" "333" "334" "335" "336" "337" "338" "339" "340" "341"
[341] "342" "343" "344" "345" "346" "347" "348" "349" "350" "351"
[351] "352" "353" "354" "355" "356" "357" "358" "359" "360" "361"
[361] "362" "363" "364" "365" "366" "367" "368" "369" "370" "371"
[371] "372" "373" "374" "375" "376" "377" "378" "379" "380" "381"
[381] "382" "383" "384" "385" "386" "387" "388" "389" "390" "391"
[391] "392" "393" "394" "395" "396" "397" "398" "399" "400" "401"
[401] "402" "403" "404" "405" "406" "407" "408" "409" "410" "411"
[411] "412" "413" "414" "415" "416" "417" "418" "419" "420" "421"
[421] "422" "423" "424" "425" "426" "427" "428" "429" "430" "431"
[431] "432" "433" "434" "435" "436" "437" "438" "439" "440" "441"
[441] "442" "443" "444" "445" "446" "447" "448" "449" "450" "451"
[451] "452" "453" "454" "455" "456" "457" "458" "459" "460" "461"
[461] "462" "463" "464" "465" "466" "467" "468" "469" "470" "471"
[471] "472" "473" "474" "475" "476" "477" "478" "479" "480" "481"
[481] "482" "483" "484" "485" "486" "487" "488" "489" "490" "491"
[491] "492" "493" "494" "495" "496" "497" "498" "499" "500" "501"
[501] "502" "503" "504" "505" "506" "507" "508" "509" "510" "511"
[511] "512" "513" "514" "515" "516" "517" "518" "519" "520" "521"
[521] "522" "523" "524" "525" "526" "527" "528" "529" "530" "531"
[531] "532" "533" "534" "535" "536" "537" "538" "539" "540" "541"
[541] "542" "543" "544" "545" "546" "547" "548" "549" "550" "551"
[551] "552" "553" "554" "555" "556" "557" "558" "559" "560" "561"
[561] "562" "563" "564" "565" "566" "567" "568" "569" "570" "571"
[571] "572" "573" "574" "575" "576" "577" "578" "579" "580" "581"
[581] "582" "583" "584" "585" "586" "587" "588" "589" "590" "591"
[591] "592" "593" "594" "595" "596" "597" "598" "599" "600" "601"
[601] "602" "603" "604" "605" "606" "608" "609" "610" "611" "612"
[611] "613" "614" "615" "616" "617" "618" "619" "620" "621" "622"
[621] "623" "624" "625" "626" "627" "628" "629" "630" "631" "632"
[631] "633" "634" "635" "636" "637" "638" "639" "640" "641" "642"
[641] "643" "644" "645" "646" "647" "648" "649" "650" "651" "652"
[651] "653" "654" "655" "656" "657" "658" "659" "660" "661" "662"
[661] "663" "664" "665" "666" "667" "668" "669" "670" "671" "672"
[671] "673" "674" "675" "676" "677" "678" "679" "680" "681" "682"
[681] "683" "684" "685" "686" "687" "688" "689" "690" "691" "692"
[691] "693" "694" "695" "696" "697" "698" "699" "700" "701" "702"
[701] "703" "704" "705" "706" "707" "708" "709" "710" "711" "712"
[711] "713" "714" "715" "716" "717" "718" "719" "720" "721" "722"
[721] "723" "724" "725" "726" "727" "728" "729" "730" "731" "732"
[731] "733" "734" "735" "736" "737" "738" "739" "740" "741" "742"
[741] "743" "744" "745" "746" "747" "748" "749" "750" "751" "752"
[751] "753" "754" "755" "756" "757" "758" "759" "760" "761" "762"
[761] "763" "764" "765" "766" "767" "768" "769" "770" "771" "772"
[771] "773" "774" "775" "776" "777" "778" "779" "780" "781" "782"
[781] "783" "784" "785" "786" "787" "789" "790" "791" "792" "793"
[791] "794" "795" "796" "797" "798" "799" "800" "801" "802" "803"
[801] "804" "805" "806" "807" "808" "809" "810" "811" "812" "813"
[811] "814" "815" "816" "817" "818" "819" "820" "821" "822" "823"
[821] "824" "825" "826" "827" "828" "829" "830" "831" "832" "833"
[831] "834" "835" "836" "837" "838" "839" "840" "841" "842" "843"
[841] "844" "845" "846" "847" "848" "849" "850" "851" "852" "853"
[851] "854" "855" "856" "857" "858" "859" "860" "861" "862" "863"
[861] "864" "865" "866" "867" "868" "869" "870" "871" "872" "873"
[871] "874" "875" "876" "877" "878" "879" "880" "881" "882" "883"
[881] "884" "885" "886" "887" "888" "889" "890" "891" "892" "893"
[891] "894" "895" "896" "897" "898" "899" "900" "901" "902" "903"
[901] "904" "905" "906" "907" "908" "909" "910" "911" "912" "913"
[911] "914" "915" "916" "917" "918" "919" "920" "921" "922" "923"
[921] "924" "925" "926" "927" "928" "929" "930" "931" "932" "933"
[931] "934" "935" "936" "937" "938" "939" "940" "941" "942" "943"
[941] "944" "945" "946" "947" "948" "949" "950" "951" "952" "953"
[951] "954" "955" "956" "957" "958" "959" "960" "961" "962" "963"
[961] "964" "965" "966" "967" "968" "969" "970" "971" "972" "973"
[971] "974" "975" "976" "977" "978" "979" "980" "981" "982" "983"
[981] "984" "985" "986" "987" "988" "989" "990" "991" "992" "993"
[991] "994" "995" "996" "997" "998" "999" "1000" "1001" "1002" "1003"
[1001] "1004" "1005" "1006" "1007" "1008" "1009" "1010" "1011" "1012" "1013"
[1011] "1014" "1015" "1016" "1017" "1018" "1019" "1020" "1021" "1022" "1023"
[1021] "1024" "1025" "1026" "1027" "1028" "1029" "1030" "1031" "1032" "1033"
[1031] "1034" "1035" "1036" "1037" "1038" "1039" "1040" "1041" "1042" "1043"
[1041] "1044" "1045" "1046" "1047" "1048" "1049" "1050" "1051" "1052" "1053"
[1051] "1054" "1055" "1056" "1057" "1058" "1059" "1060" "1061" "1062" "1063"
[1061] "1064" "1065" "1066" "1067" "1068" "1069" "1070" "1071" "1072" "1073"
[1071] "1074" "1075" "1076" "1077" "1078" "1079" "1080" "1081" "1082" "1083"
[1081] "1084" "1085" "1086" "1087" "1088" "1089" "1090" "1091" "1092" "1093"
[1091] "1094" "1095" "1096" "1097" "1098" "1100" "1101" "1102" "1103" "1104"
[1101] "1105" "1106" "1107" "1108" "1109" "1110" "1111" "1112" "1113" "1114"
[1111] "1115" "1116" "1117" "1118" "1119" "1120" "1121" "1122" "1123" "1124"
[1121] "1125" "1126" "1127" "1128" "1129" "1130" "1131" "1132" "1133" "1134"
[1131] "1135" "1136" "1137" "1138" "1139" "1140" "1141" "1142" "1143" "1144"
[1141] "1145" "1146" "1147" "1148" "1149" "1150" "1151" "1152" "1153" "1154"
[1151] "1155" "1156" "1157" "1158" "1159" "1160" "1161" "1162" "1163" "1164"
[1161] "1165" "1166" "1167" "1168" "1169" "1170" "1171" "1172" "1173" "1174"
[1171] "1175" "1176" "1177" "1178" "1179" "1180" "1181" "1182" "1183" "1184"
[1181] "1185" "1186" "1187" "1188" "1189" "1190" "1191" "1192" "1193" "1194"
[1191] "1195" "1196" "1197" "1198" "1199" "1200" "1201" "1202" "1203" "1204"
[1201] "1205" "1206" "1207" "1208" "1209" "1210" "1211" "1212" "1213" "1214"
[1211] "1215" "1216" "1217" "1218" "1219" "1220" "1221" "1222" "1223" "1224"
[1221] "1225" "1226" "1227" "1228" "1229" "1230" "1231" "1232" "1233" "1234"
[1231] "1235" "1236" "1237" "1238" "1239" "1240" "1241" "1242" "1243" "1244"
[1241] "1245" "1246" "1247" "1248" "1249" "1250" "1251" "1252" "1253" "1254"
[1251] "1255" "1256" "1257" "1258" "1259" "1260" "1261" "1262" "1263" "1264"
[1261] "1265" "1266" "1267" "1268" "1269" "1270" "1271" "1272" "1273" "1274"
[1271] "1275" "1276" "1277" "1278" "1279" "1280" "1281" "1282" "1284" "1285"
[1281] "1286" "1287" "1288" "1289" "1290" "1291" "1292" "1293" "1294" "1295"
[1291] "1296" "1297" "1298" "1299" "1300" "1301" "1302" "1303" "1304" "1305"
[1301] "1306" "1307" "1308" "1309" "1310" "1311" "1312" "1313" "1314" "1315"
[1311] "1316" "1317" "1318" "1319" "1320" "1321" "1322" "1323" "1324" "1325"
[1321] "1326" "1327" "1328" "1329" "1330" "1331" "1332" "1333" "1334" "1335"
[1331] "1336" "1337" "1338" "1339" "1340" "1341" "1342" "1343" "1344" "1345"
[1341] "1346" "1347" "1348" "1349" "1350" "1351" "1352" "1353" "1354" "1355"
[1351] "1356" "1357" "1358" "1359" "1360" "1361" "1362" "1363" "1364" "1365"
[1361] "1366" "1367" "1368" "1369" "1370" "1371" "1372" "1373" "1374" "1375"
[1371] "1376" "1377" "1378" "1379" "1380" "1381" "1382" "1383" "1384" "1385"
[1381] "1386" "1387" "1388" "1389" "1390" "1391" "1392" "1393" "1394" "1395"
[1391] "1396" "1397" "1398" "1399" "1400" "1401" "1402" "1403" "1404" "1405"
[1401] "1406" "1407" "1408" "1409" "1410" "1411" "1412" "1413" "1414" "1415"
[1411] "1416" "1417" "1418" "1419" "1420" "1421" "1422" "1423" "1424" "1425"
[1421] "1426" "1427" "1428" "1429" "1430" "1431" "1432" "1433" "1434" "1435"
[1431] "1436" "1437" "1438" "1439" "1440" "1441" "1442" "1443" "1444" "1445"
[1441] "1446" "1447" "1448" "1449" "1450" "1451" "1452" "1453" "1454" "1455"
[1451] "1456" "1457" "1458" "1459" "1460" "1461" "1462" "1463" "1464" "1465"
[1461] "1466" "1467" "1468" "1469" "1470" "1471" "1472" "1473" "1474" "1475"
[1471] "1476" "1477" "1478" "1479" "1480" "1481" "1482" "1483" "1484" "1485"
[1481] "1486" "1487" "1488" "1489" "1490" "1491" "1492" "1493" "1494" "1495"
[1491] "1496" "1497" "1498" "1499" "1500" "1501" "1502" "1503" "1504" "1505"
[1501] "1506" "1507" "1508" "1509" "1510" "1511" "1512" "1513" "1514" "1515"
[1511] "1516" "1517" "1518" "1519" "1520" "1521" "1522" "1523" "1524" "1525"
[1521] "1526" "1527" "1528" "1529" "1530" "1531" "1532" "1533" "1534" "1535"
[1531] "1536" "1537" "1538" "1539" "1540" "1541" "1542" "1543" "1544" "1545"
[1541] "1546" "1547" "1548" "1549" "1550" "1551" "1552" "1553" "1554" "1555"
[1551] "1556" "1557" "1558" "1559" "1560" "1561" "1562" "1563" "1564" "1565"
[1561] "1566" "1567" "1568" "1569" "1570" "1571" "1572" "1573" "1574" "1575"
[1571] "1576" "1577" "1578" "1579" "1580" "1581" "1582" "1583" "1584" "1585"
[1581] "1586" "1587" "1588" "1589" "1590" "1591" "1592" "1593" "1594" "1595"
[1591] "1596" "1597" "1598" "1599" "1600" "1601" "1602" "1603" "1604" "1605"
[1601] "1606" "1607" "1608" "1609" "1610" "1611" "1612" "1613" "1614" "1615"
[1611] "1616" "1617" "1618" "1619" "1620" "1621" "1622" "1623" "1624" "1625"
[1621] "1626" "1627" "1628" "1629" "1630" "1631" "1632" "1633" "1634" "1635"
[1631] "1636" "1637" "1638" "1639" "1640" "1641" "1642" "1643" "1644" "1645"
[1641] "1646" "1647" "1648" "1649" "1650" "1651" "1652" "1653" "1654" "1655"
[1651] "1656" "1657" "1658" "1659" "1660" "1661" "1662" "1663" "1664" "1665"
[1661] "1666" "1667" "1668" "1669" "1670" "1671" "1672" "1673" "1674" "1675"
[1671] "1676" "1677" "1678" "1679" "1680" "1681" "1682" "1683" "1684" "1685"
[1681] "1686" "1687" "1688" "1689" "1690" "1691" "1692" "1693" "1694" "1695"
[1691] "1696" "1697" "1698" "1699" "1700" "1701" "1702" "1703" "1704" "1705"
[1701] "1706" "1707" "1708" "1709" "1710" "1711" "1712" "1713" "1714" "1715"
[1711] "1716" "1717" "1718" "1719" "1720" "1721" "1722" "1723" "1724" "1725"
[1721] "1726" "1727" "1728" "1729" "1730" "1731" "1732" "1733" "1734" "1735"
[1731] "1736" "1737" "1738" "1739" "1740" "1741" "1742" "1743" "1744" "1745"
[1741] "1746" "1747" "1748" "1749" "1750" "1751" "1752" "1753" "1754" "1755"
[1751] "1756" "1757" "1758" "1759" "1760" "1761" "1762" "1763" "1764" "1765"
[1761] "1766" "1767" "1768" "1769" "1770" "1771" "1772" "1773" "1774" "1775"
[1771] "1776" "1777" "1778" "1779" "1780" "1781" "1782" "1783" "1784" "1785"
[1781] "1786" "1787" "1788" "1789" "1790" "1791" "1792" "1793" "1794" "1795"
[1791] "1796" "1797" "1798" "1799" "1800" "1801" "1802" "1803" "1804" "1805"
[1801] "1806" "1807" "1808" "1809" "1810" "1811" "1812" "1813" "1814" "1815"
[1811] "1816" "1817" "1818" "1819" "1820" "1821" "1822" "1823" "1824" "1825"
[1821] "1826" "1827" "1828" "1829" "1830" "1831" "1832" "1833" "1834" "1835"
[1831] "1836" "1837" "1838" "1839" "1840" "1841" "1842" "1843" "1844" "1845"
[1841] "1846" "1847" "1848" "1849" "1850" "1851" "1852" "1853" "1854" "1855"
[1851] "1856" "1857" "1858" "1859" "1860" "1861" "1862" "1863" "1864" "1865"
[1861] "1866" "1867" "1868" "1869" "1870" "1871" "1872" "1873" "1874" "1875"
[1871] "1876" "1877" "1878" "1879" "1880" "1881" "1882" "1883" "1884" "1885"
[1881] "1886" "1887" "1888" "1889" "1890" "1891" "1892" "1893" "1894" "1895"
[1891] "1896" "1897" "1898" "1899" "1900" "1901" "1902" "1903" "1904" "1905"
[1901] "1906" "1907" "1908" "1909" "1910" "1911" "1912" "1913" "1914" "1915"
[1911] "1916" "1917" "1918" "1919" "1920" "1921" "1922" "1923" "1924" "1925"
[1921] "1926" "1927"
[[2]]
[1] "sex" "age" "edu" "occ" "oexp" "income"class(incex) # type (class) of R-object: data.frame[1] "data.frame"# incex$age # extracts & prints the "age" variable from the data frame
head(incex$age) # returns the first six lines of age variable[1] 62 32 56 63 20 38class(incex$age) # class of age variable: integer vector[1] "integer"length(incex$edu) # length of the factor (number of observations)[1] 1922# incex$edu # extrats & print the factor values on the screen
head(incex$edu) # returns the first six lines of edu variable[1] "low" "high" "med." "med." "low" "med."class(incex$edu) # class of edu variable: factor (vector of categorical values)[1] "character"nlevels(incex$edu) # number of factor levels[1] 0levels(incex$edu) # levels of the factorNULLChecking available objects & search path
objects() # lists the objects accessible to you; alternatively: ls()[1] "incex" "incex.2" "incex.3" "x" "y" search() # lists attached packages, and R objects, [1] ".GlobalEnv" "package:foreign" "package:stats"
[4] "package:graphics" "package:grDevices" "package:utils"
[7] "package:datasets" "package:methods" "Autoloads"
[10] "package:base" rm(incex.2, incex.3) # removes the two data sets
objects()[1] "incex" "x" "y" Getting help
help(mean) # get help on R-objects (mostly functions)
?mean # alternative version
help.search('mean') # if you don't know the name of the function (object)
??mean # alternative version
apropos('mean') # searches for objects (incl. functions) containing "mean"
# in their name
????mean # if you still cannot find what you want
help.start() # help "menu"Creating a Vector of Sequences
# creates a vector of numeric values
# combines (concatenates) single values to a vector
c(1, 2, 3) # very frequently used (whenever you have to pass a vector to a function)![1] 1 2 3c('apple', 'tree') # combines character strings into a character vector[1] "apple" "tree" c(3, 'apple') # transforms 3 into a character string ("3")[1] "3" "apple"- EXAMPLE 1: assign/store a vector of values
x <- c(21, -3, .003)
x[1] 21.000 -3.000 0.003(y <- c('X1', 'X2', 'Y1', 'Y2')) [1] "X1" "X2" "Y1" "Y2"# putting the assingment in parentheses "()" is equivalent to print() ... print on screen - EXAMPLE 2: extract variable ‘age’ and ‘occ’ from the incex data frame
# incex[, c('age', 'occ')] # character strings 'age' and 'occ' need to be combined
head(incex[, c('age', 'occ')]) age occ
1 62 low
2 32 high
3 56 high
4 63 med.
5 20 low
6 38 med.- EXAMPLE 3: extract rows and columns from a data frame
- use the sequence operator ‘:’
1:3 # sequence of integers from 1 to 3; is the same as c(1, 2, 3)[1] 1 2 33:1 # sequence of integers from 3 to 1; is the same as c(3, 2, 1)[1] 3 2 1-25:-78 [1] -25 -26 -27 -28 -29 -30 -31 -32 -33 -34 -35 -36 -37 -38 -39 -40 -41 -42 -43
[20] -44 -45 -46 -47 -48 -49 -50 -51 -52 -53 -54 -55 -56 -57 -58 -59 -60 -61 -62
[39] -63 -64 -65 -66 -67 -68 -69 -70 -71 -72 -73 -74 -75 -76 -77 -78?':' # get help for ':'; need quotes since the colon is a special symbol
incex[1:10, c('age', 'occ')] age occ
1 62 low
2 32 high
3 56 high
4 63 med.
5 20 low
6 38 med.
7 39 low
8 53 low
9 49 med.
10 54 lowincex[1:10, c(2, 4)] age occ
1 62 low
2 32 high
3 56 high
4 63 med.
5 20 low
6 38 med.
7 39 low
8 53 low
9 49 med.
10 54 lowincex[c(1:10, 20:25), c(2, 4)] age occ
1 62 low
2 32 high
3 56 high
4 63 med.
5 20 low
6 38 med.
7 39 low
8 53 low
9 49 med.
10 54 low
20 58 high
21 26 low
22 35 high
23 34 med.
24 43 high
25 49 highc(1:10, 20:25) [1] 1 2 3 4 5 6 7 8 9 10 20 21 22 23 24 25the “sequence” function seq()
?seq
seq(from = 1, to = 3, by = 1)[1] 1 2 3seq(from = 1, by = 1, to = 3)[1] 1 2 3seq(1, 3, 1) # don't need the argument names if we list arguments in default order[1] 1 2 3seq(-2, 3, by = .25) [1] -2.00 -1.75 -1.50 -1.25 -1.00 -0.75 -0.50 -0.25 0.00 0.25 0.50 0.75
[13] 1.00 1.25 1.50 1.75 2.00 2.25 2.50 2.75 3.00seq(-2, 3, length = 20) [1] -2.0000000 -1.7368421 -1.4736842 -1.2105263 -0.9473684 -0.6842105
[7] -0.4210526 -0.1578947 0.1052632 0.3684211 0.6315789 0.8947368
[13] 1.1578947 1.4210526 1.6842105 1.9473684 2.2105263 2.4736842
[19] 2.7368421 3.0000000- EXAMPLE 1: use seq() for generating quantiles
?quantile
seq(0, 1, .25)[1] 0.00 0.25 0.50 0.75 1.00quantile(incex$income, probs = seq(0, 1, .25)) # quartiles 0% 25% 50% 75% 100%
704.00 1117.00 1304.00 1505.75 2115.00 quantile(incex$income, probs = seq(0, 1, .1)) # deciles 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100%
704.0 982.2 1081.0 1155.3 1228.4 1304.0 1383.6 1462.0 1538.0 1650.9 2115.0 seq(0, 1, .1) [1] 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0- EXAMPLE 2: use seq() for plotting histograms
?hist
hist(incex$income, breaks = seq(500, 2500, 100)) # bin-width of 100 EUR 
hist(incex$income, breaks = seq(500, 2500, 50)) # bin-width of 50 EUR
- EXAMPLE 3: use seq() for generating names (e.g., for factor levels or plotting)
?paste
paste('age:', seq(15, 70, 5)) # paste() builds a vector of character strings [1] "age: 15" "age: 20" "age: 25" "age: 30" "age: 35" "age: 40" "age: 45"
[8] "age: 50" "age: 55" "age: 60" "age: 65" "age: 70"paste('age: ', seq(15, 70, 5), '-', seq(19, 74, 5), ' years', sep = '') [1] "age: 15-19 years" "age: 20-24 years" "age: 25-29 years" "age: 30-34 years"
[5] "age: 35-39 years" "age: 40-44 years" "age: 45-49 years" "age: 50-54 years"
[9] "age: 55-59 years" "age: 60-64 years" "age: 65-69 years" "age: 70-74 years" # shorter vectors (e.g., 'age', '-', are automatically recycled!the “replicate” function rep()
rep(7, times = 10) [1] 7 7 7 7 7 7 7 7 7 7rep(7, 10) [1] 7 7 7 7 7 7 7 7 7 7rep(1:3, 10) [1] 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3 1 2 3rep(1:3, each = 10) [1] 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3rep(1:3, c(2, 5, 7)) [1] 1 1 2 2 2 2 2 3 3 3 3 3 3 3?rep
rep(c(5, -1, 3, 0), each = 3) [1] 5 5 5 -1 -1 -1 3 3 3 0 0 0rep(c('one', 'two', 'three'), 1:3) # works also with character strings[1] "one" "two" "two" "three" "three" "three"- EXAMPLE: generate a combination of character strings (or create factor combinations)
A <- paste(rep('a', 5), 1:5, sep = '')# two factors A and B with 5 and 10 factor levels each:
# a1, a2, ..., a5, and b1, b2, ..., b10
# first, create vector of factor levels:
(A <- paste(rep('a', 5), 1:5, sep = ''))[1] "a1" "a2" "a3" "a4" "a5"(A <- paste('a', 1:5, sep = '')) # even shorter (R recycles 'a' five times)[1] "a1" "a2" "a3" "a4" "a5"(B <- paste('b', 1:10, sep = '')) [1] "b1" "b2" "b3" "b4" "b5" "b6" "b7" "b8" "b9" "b10"# second, create all possible combinations of A and B
cbind(rep(A, each = 10), rep(B, 5)) # cbind() binds the two vectors into a column matrix [,1] [,2]
[1,] "a1" "b1"
[2,] "a1" "b2"
[3,] "a1" "b3"
[4,] "a1" "b4"
[5,] "a1" "b5"
[6,] "a1" "b6"
[7,] "a1" "b7"
[8,] "a1" "b8"
[9,] "a1" "b9"
[10,] "a1" "b10"
[11,] "a2" "b1"
[12,] "a2" "b2"
[13,] "a2" "b3"
[14,] "a2" "b4"
[15,] "a2" "b5"
[16,] "a2" "b6"
[17,] "a2" "b7"
[18,] "a2" "b8"
[19,] "a2" "b9"
[20,] "a2" "b10"
[21,] "a3" "b1"
[22,] "a3" "b2"
[23,] "a3" "b3"
[24,] "a3" "b4"
[25,] "a3" "b5"
[26,] "a3" "b6"
[27,] "a3" "b7"
[28,] "a3" "b8"
[29,] "a3" "b9"
[30,] "a3" "b10"
[31,] "a4" "b1"
[32,] "a4" "b2"
[33,] "a4" "b3"
[34,] "a4" "b4"
[35,] "a4" "b5"
[36,] "a4" "b6"
[37,] "a4" "b7"
[38,] "a4" "b8"
[39,] "a4" "b9"
[40,] "a4" "b10"
[41,] "a5" "b1"
[42,] "a5" "b2"
[43,] "a5" "b3"
[44,] "a5" "b4"
[45,] "a5" "b5"
[46,] "a5" "b6"
[47,] "a5" "b7"
[48,] "a5" "b8"
[49,] "a5" "b9"
[50,] "a5" "b10"cbind(rep(A, each = 10), B) # shorter: use the recycling rule B
[1,] "a1" "b1"
[2,] "a1" "b2"
[3,] "a1" "b3"
[4,] "a1" "b4"
[5,] "a1" "b5"
[6,] "a1" "b6"
[7,] "a1" "b7"
[8,] "a1" "b8"
[9,] "a1" "b9"
[10,] "a1" "b10"
[11,] "a2" "b1"
[12,] "a2" "b2"
[13,] "a2" "b3"
[14,] "a2" "b4"
[15,] "a2" "b5"
[16,] "a2" "b6"
[17,] "a2" "b7"
[18,] "a2" "b8"
[19,] "a2" "b9"
[20,] "a2" "b10"
[21,] "a3" "b1"
[22,] "a3" "b2"
[23,] "a3" "b3"
[24,] "a3" "b4"
[25,] "a3" "b5"
[26,] "a3" "b6"
[27,] "a3" "b7"
[28,] "a3" "b8"
[29,] "a3" "b9"
[30,] "a3" "b10"
[31,] "a4" "b1"
[32,] "a4" "b2"
[33,] "a4" "b3"
[34,] "a4" "b4"
[35,] "a4" "b5"
[36,] "a4" "b6"
[37,] "a4" "b7"
[38,] "a4" "b8"
[39,] "a4" "b9"
[40,] "a4" "b10"
[41,] "a5" "b1"
[42,] "a5" "b2"
[43,] "a5" "b3"
[44,] "a5" "b4"
[45,] "a5" "b5"
[46,] "a5" "b6"
[47,] "a5" "b7"
[48,] "a5" "b8"
[49,] "a5" "b9"
[50,] "a5" "b10"# create a vector of character strings (of combinations)
paste(rep(A, each = 10), rep(B, 5), sep = '*') [1] "a1*b1" "a1*b2" "a1*b3" "a1*b4" "a1*b5" "a1*b6" "a1*b7" "a1*b8"
[9] "a1*b9" "a1*b10" "a2*b1" "a2*b2" "a2*b3" "a2*b4" "a2*b5" "a2*b6"
[17] "a2*b7" "a2*b8" "a2*b9" "a2*b10" "a3*b1" "a3*b2" "a3*b3" "a3*b4"
[25] "a3*b5" "a3*b6" "a3*b7" "a3*b8" "a3*b9" "a3*b10" "a4*b1" "a4*b2"
[33] "a4*b3" "a4*b4" "a4*b5" "a4*b6" "a4*b7" "a4*b8" "a4*b9" "a4*b10"
[41] "a5*b1" "a5*b2" "a5*b3" "a5*b4" "a5*b5" "a5*b6" "a5*b7" "a5*b8"
[49] "a5*b9" "a5*b10"Basic Data Manipulations
Accessing a data frame (selecting columns & rows)
incex$age # selects 'age'-variable using $
incex[, 'age'] # selects 'age'-variable using [..]
incex[, 2] # selects 2nd columnincex[1:10, ] # selects rows 1 to 10 sex age edu occ oexp income
1 f 62 low low 35 953
2 m 32 high high 6 1224
3 m 56 med. high 36 1466
4 f 63 med. med. 38 1339
5 m 20 low low 3 1184
6 f 38 med. med. 12 1196
7 f 39 med. low 13 951
8 f 53 low low 30 1039
9 m 49 low med. 31 1438
10 f 54 low low 30 1000incex[1:10, 2] # selects rows 1 to 10 of age [1] 62 32 56 63 20 38 39 53 49 54incex[1:10, 'age'] # selects rows 1 to 10 of age [1] 62 32 56 63 20 38 39 53 49 54incex$age[1:10] # first select age then rows 1 to 10 [1] 62 32 56 63 20 38 39 53 49 54- EXAMPLE: select a random sample of 20 observations
smpl.ind <- sample(1:nrow(incex), size = 20)
smpl.ind [1] 1356 1087 1819 1908 1472 67 1644 269 857 1688 1282 753 576 1428 279
[16] 331 1181 1349 1043 38incex[smpl.ind, ] sex age edu occ oexp income
1361 m 43 low med. 25 1034
1090 m 43 med. med. 21 1402
1824 m 47 med. med. 26 1538
1913 m 30 low med. 11 1075
1477 f 39 low low 19 1034
67 m 27 low low 10 1141
1649 f 22 high high 0 1385
269 f 25 low low 3 853
860 m 44 med. med. 24 1119
1693 m 27 low low 9 937
1287 f 55 low med. 35 1385
755 m 57 med. med. 36 1506
577 m 24 low low 5 1053
1433 m 42 high high 16 1772
279 m 29 high high 4 1624
332 f 62 med. med. 38 1240
1185 m 52 low med. 33 1425
1354 f 35 med. med. 9 1168
1046 f 48 high high 19 1432
38 m 45 med. high 24 1593# alternatively (without creating the smpl.ind object):
incex[sample(1:nrow(incex), size = 20), ] sex age edu occ oexp income
831 m 27 low low 9 1263
1667 m 28 med. med. 7 1377
601 m 46 med. low 24 1423
1775 m 53 high high 28 1769
1357 m 27 high high 2 1579
1755 m 30 med. med. 8 1363
634 m 50 low med. 31 1206
473 f 58 low low 36 1226
883 m 40 high high 15 1546
830 m 47 med. med. 27 1433
466 m 37 low med. 19 1397
1494 f 57 low low 34 1233
308 m 54 low med. 36 1309
1255 f 33 low low 13 999
1155 f 42 med. med. 17 1217
1669 m 22 high med. 0 1290
313 f 23 med. low 0 1104
1321 f 25 low low 4 879
862 m 27 med. med. 5 1235
1814 f 24 low low 0 780Selecting subsets of data using indices
age <- incex$age # creates new object of name "age" (ie, creates a copy)
dim(age) # does not work since age is no longer a data frame but a vectorNULLlength(age)[1] 1922age[10:20] # only one argument in brackets since a vector has only [1] 54 51 52 25 58 40 59 31 48 34 58 # one dimension (rows)
age[seq(1, length(age), by = 5)] # select each 5th value (starting with first obs.) [1] 62 38 51 59 26 39 38 59 37 44 24 45 28 51 45 59 47 18 19 51 36 58 46 47 56
[26] 22 51 62 22 62 55 50 35 39 25 37 44 57 36 48 19 59 48 54 33 52 42 45 50 37
[51] 36 31 35 25 33 41 29 36 43 35 27 29 40 25 25 26 62 18 50 36 42 44 56 36 35
[76] 58 28 26 27 37 48 36 60 58 53 57 25 35 23 58 45 38 42 26 26 39 65 26 24 60
[101] 42 60 45 52 63 51 24 39 58 28 39 37 51 47 30 24 31 20 41 39 30 31 58 28 57
[126] 42 52 25 39 40 40 31 41 22 27 23 52 53 27 60 40 42 35 47 27 47 34 34 32 57
[151] 53 45 32 47 42 55 28 31 54 25 52 42 39 62 53 50 25 45 59 40 56 55 24 34 44
[176] 46 25 43 59 37 60 25 51 54 42 38 48 31 53 26 38 46 26 55 35 27 57 38 42 51
[201] 33 31 41 53 36 47 51 39 57 23 55 49 45 43 64 31 19 53 60 45 59 40 35 33 50
[226] 24 55 36 40 59 42 25 52 39 52 52 52 49 38 54 30 46 54 37 32 54 51 41 48 46
[251] 33 39 41 28 25 36 26 40 46 24 43 50 54 25 26 40 60 60 30 28 23 43 41 32 52
[276] 42 63 53 43 49 60 43 30 43 37 51 37 50 28 32 43 30 23 61 37 50 51 42 37 57
[301] 47 55 41 46 24 32 47 64 33 33 38 27 57 54 37 27 42 26 25 48 32 34 55 24 27
[326] 36 35 35 37 60 21 23 53 37 36 29 31 60 48 30 21 49 46 56 58 49 43 29 22 48
[351] 32 21 29 39 42 44 22 30 36 49 42 58 55 32 40 60 49 57 26 34 57 31 54 51 47
[376] 30 58 24 53 23 26 52 29 31 59age[-(10:1700)] # all values except values #10 to #1700 [1] 62 32 56 63 20 38 39 53 49 21 49 18 27 30 49 53 37 58 51 46 45 27 32 42 56
[26] 42 64 25 51 58 39 24 24 40 49 30 51 35 34 43 55 58 37 54 29 41 34 55 62 22
[51] 43 46 27 55 48 64 58 62 30 32 54 32 47 30 21 52 37 51 43 29 23 53 25 53 39
[76] 36 48 35 53 42 39 25 35 54 44 48 41 47 36 22 42 39 21 54 30 25 64 36 32 36
[101] 56 39 61 54 49 30 44 58 46 42 41 55 24 54 58 26 58 24 32 55 51 30 62 43 32
[126] 58 29 47 38 40 42 57 26 22 60 35 50 32 26 49 37 34 52 37 57 38 48 25 49 26
[151] 32 42 30 26 34 46 47 23 29 57 55 28 56 52 31 19 53 62 26 54 37 52 48 56 51
[176] 26 62 36 22 47 44 33 54 45 30 33 33 30 56 58 35 28 64 45 24 60 32 41 58 53
[201] 31 39 40 45 23 34 28 50 62 26 56 41 41 32 52 48 30 53 55 29 46 45 33 35 31
[226] 28 25 33 35 59 57age[-c(1:9, 21:length(age))] # all values except ... [1] 54 51 52 25 58 40 59 31 48 34 58Sorting data
# sort age from the smallest to largest value
# note: the age variable 'age' remains unsorted since we
sort(age) # didn't save the sorted vector: age <- sort(age) [1] 18 18 18 18 18 18 18 18 18 18 18 18 19 19 19 19 19 19 19 19 20 20 20 20
[25] 20 20 20 20 20 20 20 20 20 20 20 21 21 21 21 21 21 21 21 21 21 21 21 21
[49] 21 21 21 21 21 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22 22
[73] 22 22 22 22 22 22 22 22 22 22 23 23 23 23 23 23 23 23 23 23 23 23 23 23
[97] 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 23 24 24 24 24 24 24 24
[121] 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24 24
[145] 24 24 24 24 24 24 24 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25
[169] 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25
[193] 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 25 26 26 26
[217] 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26
[241] 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 26 27 27 27
[265] 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27
[289] 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 27 28
[313] 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28 28
[337] 28 28 28 28 28 28 28 28 28 28 28 28 28 29 29 29 29 29 29 29 29 29 29 29
[361] 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29 29
[385] 29 29 29 29 29 29 29 29 29 29 29 29 29 29 30 30 30 30 30 30 30 30 30 30
[409] 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30
[433] 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 30 31 31 31 31 31 31 31 31
[457] 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31 31
[481] 31 31 31 31 31 31 31 31 31 31 31 31 32 32 32 32 32 32 32 32 32 32 32 32
[505] 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32
[529] 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 32 33 33 33 33 33 33 33 33
[553] 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33 33
[577] 33 33 33 33 33 33 33 33 33 33 33 34 34 34 34 34 34 34 34 34 34 34 34 34
[601] 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34 34
[625] 34 34 34 34 34 34 34 34 34 34 34 34 34 35 35 35 35 35 35 35 35 35 35 35
[649] 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35 35
[673] 35 35 35 35 35 35 35 35 35 35 35 35 35 36 36 36 36 36 36 36 36 36 36 36
[697] 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36 36
[721] 36 36 36 36 36 36 36 36 36 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37
[745] 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37 37
[769] 37 37 37 37 37 37 37 37 37 37 37 37 37 37 38 38 38 38 38 38 38 38 38 38
[793] 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 39 39 39 39
[817] 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39
[841] 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 39 40 40 40 40
[865] 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40
[889] 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 40 41 41 41 41 41 41
[913] 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41
[937] 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 41 42 42 42 42 42 42
[961] 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42
[985] 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 42 43
[1009] 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43
[1033] 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 43 44 44 44 44 44 44
[1057] 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44 44
[1081] 44 44 44 44 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45
[1105] 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45 45
[1129] 45 45 45 45 45 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46
[1153] 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 46 47
[1177] 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47
[1201] 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 47 48
[1225] 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48
[1249] 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48 48
[1273] 48 48 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49
[1297] 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49
[1321] 49 49 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50
[1345] 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 50 51 51 51 51 51
[1369] 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51
[1393] 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51 51
[1417] 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52
[1441] 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52 52
[1465] 52 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53
[1489] 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53 53
[1513] 53 53 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54
[1537] 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 54 55 55 55 55 55 55 55 55
[1561] 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55 55
[1585] 55 55 55 55 55 55 55 55 55 55 55 55 56 56 56 56 56 56 56 56 56 56 56 56
[1609] 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56 56
[1633] 56 56 56 56 56 56 56 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57
[1657] 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57 57
[1681] 57 57 57 57 57 57 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
[1705] 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58 58
[1729] 58 58 58 58 58 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59
[1753] 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59 59
[1777] 59 59 59 59 59 59 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60
[1801] 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 60 61 61 61 61
[1825] 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 61 62 62 62 62
[1849] 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62 62
[1873] 62 62 62 62 62 62 62 62 63 63 63 63 63 63 63 63 63 63 63 63 63 63 63 63
[1897] 63 63 63 64 64 64 64 64 64 64 64 64 64 64 64 64 64 64 65 65 65 65 65 65
[1921] 65 65order(age) # returns the sorting index (for sorting) [1] 27 86 336 473 554 570 888 1037 1133 1244 1464 1703 91 201
[15] 353 470 480 1081 1407 1857 5 53 300 580 585 586 609 673
[29] 748 817 989 1013 1018 1325 1515 88 158 280 399 448 679 860
[43] 1109 1290 1430 1498 1560 1602 1651 1659 1701 1756 1784 98 126 141
[57] 232 313 337 485 495 666 693 984 1014 1135 1197 1265 1288 1305
[71] 1329 1417 1418 1448 1482 1618 1644 1664 1741 1781 1825 1870 57 93
[85] 145 184 205 215 312 324 385 403 427 441 676 758 994 1046
[99] 1059 1078 1113 1298 1323 1345 1351 1461 1492 1512 1656 1674 1762 1849
[113] 1896 51 114 119 143 463 491 531 576 640 664 747 819 850
[127] 861 908 942 960 973 1053 1084 1094 1104 1126 1293 1296 1310 1322
[141] 1373 1415 1429 1521 1544 1616 1723 1724 1804 1809 1886 13 47 60
[155] 110 123 171 182 266 269 274 316 321 431 573 636 642 672
[169] 723 762 784 796 802 818 831 881 897 906 969 1003 1118 1152
[183] 1156 1159 1188 1232 1247 1271 1279 1316 1353 1379 1394 1432 1450 1463
[197] 1499 1519 1525 1591 1609 1613 1615 1649 1660 1677 1700 1719 1764 1773
[211] 1787 1839 1918 21 125 326 373 386 428 435 443 466 471 486
[225] 499 510 613 633 677 793 815 946 957 961 993 995 1122 1157
[239] 1168 1203 1222 1257 1281 1294 1320 1321 1369 1442 1529 1537 1586 1612
[253] 1697 1807 1824 1830 1841 1845 1860 1867 1901 67 127 129 142 222
[267] 240 301 329 333 390 391 407 469 540 542 595 659 667 671
[281] 683 691 703 721 760 803 828 859 976 1020 1025 1052 1119 1164
[295] 1218 1248 1352 1443 1513 1556 1565 1576 1621 1622 1639 1658 1687 1688
[309] 1704 1713 1744 29 61 189 220 253 381 546 616 744 763 781
[323] 855 990 997 1075 1082 1142 1148 1264 1266 1346 1348 1350 1367 1398
[337] 1400 1441 1467 1474 1579 1588 1625 1640 1662 1853 1883 1898 1917 63
[351] 128 172 177 248 279 281 287 288 306 349 425 434 557 574
[365] 628 718 740 799 812 863 914 948 1040 1080 1115 1180 1200 1255
[379] 1287 1358 1364 1365 1408 1413 1414 1455 1532 1570 1583 1592 1655 1673
[393] 1676 1736 1761 1818 1850 1911 34 48 120 162 188 325 444 457
[407] 478 563 571 594 601 654 708 729 889 915 1004 1015 1028 1067
[421] 1097 1139 1140 1183 1201 1214 1339 1341 1411 1423 1456 1483 1595 1608
[435] 1617 1634 1696 1705 1727 1750 1755 1786 1797 1813 1844 1876 1879 1908
[449] 17 90 256 283 357 375 442 498 548 581 606 656 660 694
[463] 738 769 786 804 824 848 873 910 936 978 1006 1076 1098 1154
[477] 1175 1210 1223 1237 1269 1340 1377 1462 1470 1514 1550 1562 1681 1856
[491] 1892 1916 2 95 124 170 252 259 270 323 338 343 455 583
[505] 587 592 603 685 741 759 761 772 820 890 972 985 1160 1179
[519] 1221 1242 1253 1330 1334 1366 1446 1468 1505 1520 1526 1574 1585 1594
[533] 1601 1672 1714 1751 1753 1790 1810 1816 1829 1842 1888 1905 213 221
[547] 263 271 282 294 389 404 433 460 504 514 560 577 665 690
[561] 707 710 728 788 893 1001 1062 1095 1116 1117 1169 1235 1251 1397
[575] 1409 1475 1502 1541 1546 1627 1654 1683 1873 1877 1878 1914 1919 19
[589] 23 52 79 173 218 239 449 490 512 535 634 668 697 731
[603] 736 754 840 843 866 869 933 937 962 974 1008 1057 1064 1162
[617] 1263 1277 1284 1312 1335 1354 1390 1439 1445 1507 1538 1553 1593 1606
[631] 1645 1667 1730 1738 1833 1846 1897 22 62 161 179 261 296 345
[645] 371 436 502 505 509 579 614 623 635 638 711 727 949 971
[659] 983 988 1093 1100 1111 1120 1220 1225 1229 1239 1317 1319 1349 1355
[673] 1374 1485 1533 1631 1632 1636 1729 1769 1774 1827 1882 1915 1920 37
[687] 50 69 101 113 191 204 251 286 295 315 319 346 366 368
[701] 406 418 575 795 807 852 945 982 1021 1022 1042 1090 1130 1136
[715] 1207 1276 1370 1405 1438 1449 1559 1567 1626 1671 1767 1780 1789 1791
[729] 1869 41 49 94 176 225 234 246 293 303 396 422 465 525
[743] 555 556 724 750 800 844 872 896 898 928 943 1010 1185 1189
[757] 1216 1238 1308 1357 1359 1421 1431 1444 1454 1465 1471 1491 1528 1534
[771] 1540 1554 1571 1575 1641 1666 1708 1734 1758 1832 1835 1862 6 31
[785] 45 73 87 363 439 456 503 522 608 720 742 904 912 926
[799] 951 977 986 1127 1184 1191 1199 1338 1410 1551 1578 1600 1820 1837
[813] 7 26 166 185 192 250 328 377 437 475 476 520 532 536
[827] 549 551 596 641 699 734 752 757 764 811 829 832 909 920
[841] 968 1036 1065 1125 1153 1166 1256 1309 1387 1472 1523 1543 1552 1675
[855] 1722 1766 1772 1783 1793 1893 15 74 139 217 242 275 311 317
[869] 330 340 372 388 559 568 588 646 647 651 701 755 790 792
[883] 845 846 880 903 913 1048 1106 1141 1286 1289 1326 1372 1382 1385
[897] 1460 1478 1582 1587 1589 1590 1630 1725 1821 1894 89 147 202 254
[911] 255 276 292 304 305 370 402 477 494 591 602 644 650 661
[925] 682 779 813 833 902 924 1011 1024 1034 1035 1149 1236 1261 1361
[939] 1402 1440 1488 1497 1511 1558 1584 1670 1693 1694 1737 1778 1802 1889
[953] 1903 1904 58 154 157 200 231 344 351 365 378 383 394 432
[967] 461 492 501 507 553 626 648 678 687 706 737 771 783 806
[981] 854 870 874 921 991 1044 1143 1144 1151 1228 1245 1252 1376 1428
[995] 1457 1486 1503 1581 1603 1647 1715 1717 1771 1782 1801 1822 1843 24
[1009] 77 212 233 291 350 367 452 467 584 599 605 625 680 775
[1023] 886 1023 1027 1066 1087 1102 1112 1114 1202 1204 1295 1301 1304 1332
[1037] 1356 1391 1406 1416 1451 1509 1569 1580 1692 1699 1731 1742 1760 1815
[1051] 46 100 104 148 181 198 223 267 278 334 348 356 358 398
[1065] 414 423 459 662 719 849 857 871 950 1134 1155 1230 1307 1389
[1079] 1425 1477 1510 1776 1798 1872 38 55 56 59 71 109 112 115
[1093] 134 195 236 244 310 392 451 511 515 517 643 652 713 732
[1107] 733 756 774 834 836 935 1032 1061 1092 1096 1099 1167 1182 1243
[1121] 1254 1260 1280 1480 1564 1599 1635 1678 1712 1875 1885 1895 1913 83
[1135] 97 111 160 168 243 268 342 379 488 572 582 600 639 730
[1149] 773 853 876 918 952 956 970 1050 1068 1110 1129 1158 1178 1198
[1163] 1206 1246 1291 1327 1487 1516 1530 1652 1711 1743 1800 1847 1912 81
[1177] 92 116 155 183 190 249 302 360 374 382 430 440 497 524
[1191] 564 565 566 612 688 692 716 726 766 787 827 923 1017 1019
[1205] 1026 1190 1193 1205 1384 1393 1452 1501 1531 1535 1629 1642 1650 1684
[1219] 1754 1779 1819 1848 1871 18 68 140 159 196 208 210 211 228
[1233] 285 401 453 484 527 539 610 620 674 702 715 745 765 822
[1247] 867 892 931 954 1033 1043 1069 1124 1213 1240 1241 1272 1273 1424
[1261] 1557 1573 1596 1598 1653 1679 1691 1695 1746 1768 1777 1838 1864 1907
[1275] 9 25 103 108 152 178 207 229 238 260 408 409 410 412
[1289] 534 569 607 629 670 714 794 798 838 865 883 894 899 1029
[1303] 1056 1186 1209 1215 1347 1363 1396 1437 1469 1473 1495 1542 1555 1620
[1317] 1702 1706 1726 1796 1831 1840 130 156 197 241 284 297 341 380
[1331] 429 445 627 632 658 663 675 826 864 1054 1063 1121 1165 1172
[1345] 1174 1250 1285 1297 1306 1314 1360 1375 1395 1436 1447 1476 1484 1494
[1359] 1508 1545 1657 1828 1899 11 28 30 44 66 82 96 102 107
[1373] 131 203 362 479 526 558 561 622 653 739 743 768 797 835
[1387] 911 929 940 996 998 1000 1009 1012 1031 1047 1070 1137 1147 1231
[1401] 1302 1404 1426 1453 1481 1524 1539 1623 1633 1680 1710 1720 1728 1759
[1415] 1812 1866 12 78 105 133 164 187 219 226 265 290 387 438
[1429] 464 516 518 533 547 562 631 681 801 810 878 879 884 887
[1443] 930 934 979 1039 1060 1161 1171 1176 1181 1192 1337 1371 1388 1433
[1457] 1479 1517 1605 1610 1757 1834 1855 1863 1906 8 35 132 149 235
[1471] 354 421 483 529 530 545 597 619 649 686 705 751 809 821
[1485] 825 862 885 941 964 975 999 1016 1049 1085 1086 1128 1212 1224
[1499] 1270 1343 1378 1386 1399 1412 1638 1661 1685 1707 1763 1765 1770 1858
[1513] 1891 1909 10 194 216 307 320 332 364 397 405 474 537 618
[1527] 645 791 877 916 917 1105 1170 1195 1196 1211 1226 1311 1315 1328
[1541] 1403 1548 1566 1665 1735 1752 1775 1785 1795 1805 1861 1874 40 70
[1555] 151 167 384 419 447 450 454 593 615 700 767 776 785 823
[1569] 839 856 875 900 932 966 1005 1051 1055 1089 1107 1131 1145 1282
[1583] 1435 1458 1506 1611 1624 1669 1690 1732 1739 1745 1803 1811 1852 1910
[1597] 3 42 75 117 121 138 180 214 262 264 314 359 361 500
[1611] 523 567 657 830 842 851 938 965 992 1038 1103 1123 1150 1208
[1625] 1434 1493 1563 1568 1572 1597 1607 1648 1689 1716 1792 1854 1865 1880
[1639] 1902 32 33 39 64 122 144 163 174 186 193 199 245 318
[1653] 355 393 426 482 489 621 624 689 725 746 753 837 927 980
[1667] 981 987 1041 1083 1234 1262 1313 1420 1489 1490 1496 1522 1547 1561
[1681] 1668 1698 1823 1836 1851 1922 14 20 106 137 257 299 327 369
[1695] 376 416 446 472 493 519 538 541 552 611 617 630 669 770
[1709] 782 789 922 925 939 967 1007 1074 1187 1194 1219 1275 1278 1527
[1723] 1577 1709 1721 1733 1748 1799 1806 1808 1817 1881 1890 16 36 76
[1737] 80 85 153 206 224 272 273 308 309 322 347 352 395 424
[1751] 458 468 528 598 704 709 749 777 780 841 882 891 947 955
[1765] 1101 1138 1146 1163 1217 1233 1258 1259 1299 1300 1344 1362 1380 1422
[1779] 1604 1614 1643 1921 43 118 135 165 339 411 496 506 550 578
[1793] 589 590 695 696 712 814 847 901 953 1045 1058 1073 1077 1079
[1807] 1091 1177 1267 1268 1318 1331 1336 1392 1401 1518 1646 1686 1826 1887
[1821] 54 99 169 258 298 462 544 637 808 868 905 944 958 1088
[1835] 1303 1342 1459 1466 1504 1549 1619 1628 1663 1794 1 65 72 136
[1849] 146 175 230 331 335 413 487 604 655 698 722 735 778 805
[1863] 816 907 959 963 1002 1072 1227 1274 1283 1324 1383 1682 1740 1749
[1877] 1814 1859 1868 1900 4 150 400 415 420 508 521 543 684 1030
[1891] 1108 1132 1249 1292 1333 1381 1419 1427 1637 84 209 227 237 289
[1905] 417 717 895 919 1071 1536 1718 1747 1788 1884 247 277 481 513
[1919] 858 1173 1368 1500 # the first element implies that the samllest one is located on...
rank(age) # return the rank (with ties) [1] 1862.5 518.5 1618.0 1890.0 28.0 797.5 836.5 1490.0 1298.5 1533.5
[11] 1390.0 1441.0 182.5 1710.0 883.5 1758.0 470.5 1249.0 612.5 1710.0
[21] 237.5 661.5 612.5 1029.0 1298.5 836.5 6.5 1390.0 330.5 1390.0
[31] 797.5 1663.0 1663.0 423.5 1490.0 1758.0 707.5 1109.0 1663.0 1574.5
[41] 756.0 1618.0 1801.5 1390.0 797.5 1067.5 182.5 423.5 756.0 707.5
[51] 132.5 612.5 28.0 1832.5 1109.0 1109.0 98.0 981.0 1109.0 182.5
[61] 330.5 661.5 374.0 1663.0 1862.5 1390.0 286.5 1249.0 707.5 1574.5
[71] 1109.0 1862.5 797.5 883.5 1618.0 1758.0 1029.0 1441.0 612.5 1758.0
[81] 1199.5 1390.0 1154.5 1907.0 1758.0 6.5 797.5 44.5 930.5 470.5
[91] 16.5 1199.5 98.0 756.0 518.5 1390.0 1154.5 68.0 1832.5 1067.5
[101] 707.5 1390.0 1298.5 1067.5 1441.0 1710.0 1390.0 1298.5 1109.0 182.5
[111] 1154.5 1109.0 707.5 132.5 1109.0 1199.5 1618.0 1801.5 132.5 423.5
[121] 1618.0 1663.0 182.5 518.5 237.5 68.0 286.5 374.0 286.5 1343.0
[131] 1390.0 1490.0 1441.0 1109.0 1801.5 1862.5 1710.0 1618.0 883.5 1249.0
[141] 68.0 286.5 132.5 1663.0 98.0 1862.5 930.5 1067.5 1490.0 1890.0
[151] 1574.5 1298.5 1758.0 981.0 1199.5 1343.0 981.0 44.5 1249.0 1154.5
[161] 661.5 423.5 1663.0 1441.0 1801.5 836.5 1574.5 1154.5 1832.5 518.5
[171] 182.5 374.0 612.5 1663.0 1862.5 756.0 374.0 1298.5 661.5 1618.0
[181] 1067.5 182.5 1199.5 98.0 836.5 1663.0 1441.0 423.5 330.5 1199.5
[191] 707.5 836.5 1663.0 1533.5 1109.0 1249.0 1343.0 1067.5 1663.0 981.0
[201] 16.5 930.5 1390.0 707.5 98.0 1758.0 1298.5 1249.0 1907.0 1249.0
[211] 1249.0 1029.0 566.0 1618.0 98.0 1533.5 883.5 612.5 1441.0 330.5
[221] 566.0 286.5 1067.5 1758.0 756.0 1441.0 1907.0 1249.0 1298.5 1862.5
[231] 981.0 68.0 1029.0 756.0 1490.0 1109.0 1907.0 1298.5 612.5 286.5
[241] 1343.0 883.5 1154.5 1109.0 1663.0 756.0 1918.5 374.0 1199.5 836.5
[251] 707.5 518.5 330.5 930.5 930.5 470.5 1710.0 1832.5 518.5 1298.5
[261] 661.5 1618.0 566.0 1618.0 1441.0 182.5 1067.5 1154.5 182.5 518.5
[271] 566.0 1758.0 1758.0 182.5 883.5 930.5 1918.5 1067.5 374.0 44.5
[281] 374.0 566.0 470.5 1343.0 1249.0 707.5 374.0 374.0 1907.0 1441.0
[291] 1029.0 930.5 756.0 566.0 707.5 661.5 1343.0 1832.5 1710.0 28.0
[301] 286.5 1199.5 756.0 930.5 930.5 374.0 1533.5 1758.0 1758.0 1109.0
[311] 883.5 98.0 68.0 1618.0 707.5 182.5 883.5 1663.0 707.5 1533.5
[321] 182.5 1758.0 518.5 98.0 423.5 237.5 1710.0 836.5 286.5 883.5
[331] 1862.5 1533.5 286.5 1067.5 1862.5 6.5 68.0 518.5 1801.5 883.5
[341] 1343.0 1154.5 518.5 981.0 661.5 707.5 1758.0 1067.5 374.0 1029.0
[351] 981.0 1758.0 16.5 1490.0 1663.0 1067.5 470.5 1067.5 1618.0 1199.5
[361] 1618.0 1390.0 797.5 1533.5 981.0 707.5 1029.0 707.5 1710.0 930.5
[371] 661.5 883.5 237.5 1199.5 470.5 1710.0 836.5 981.0 1154.5 1343.0
[381] 330.5 1199.5 981.0 1574.5 98.0 237.5 1441.0 883.5 566.0 286.5
[391] 286.5 1109.0 1663.0 981.0 1758.0 756.0 1533.5 1067.5 44.5 1890.0
[401] 1249.0 930.5 98.0 566.0 1533.5 707.5 286.5 1298.5 1298.5 1298.5
[411] 1801.5 1298.5 1862.5 1067.5 1890.0 1710.0 1907.0 707.5 1574.5 1890.0
[421] 1490.0 756.0 1067.5 1758.0 374.0 1663.0 98.0 237.5 1343.0 1199.5
[431] 182.5 981.0 566.0 374.0 237.5 661.5 836.5 1441.0 797.5 1199.5
[441] 98.0 470.5 237.5 423.5 1343.0 1710.0 1574.5 44.5 612.5 1574.5
[451] 1109.0 1029.0 1249.0 1574.5 518.5 797.5 423.5 1758.0 1067.5 566.0
[461] 981.0 1832.5 132.5 1441.0 756.0 237.5 1029.0 1758.0 286.5 16.5
[471] 237.5 1710.0 6.5 1533.5 836.5 836.5 930.5 423.5 1390.0 16.5
[481] 1918.5 1663.0 1490.0 1249.0 68.0 237.5 1862.5 1154.5 1663.0 612.5
[491] 132.5 981.0 1710.0 930.5 68.0 1801.5 1199.5 470.5 237.5 1618.0
[501] 981.0 661.5 797.5 566.0 661.5 1801.5 981.0 1890.0 661.5 237.5
[511] 1109.0 612.5 1918.5 566.0 1109.0 1441.0 1109.0 1441.0 1710.0 836.5
[521] 1890.0 797.5 1618.0 1199.5 756.0 1390.0 1249.0 1758.0 1490.0 1490.0
[531] 132.5 836.5 1441.0 1298.5 612.5 836.5 1533.5 1710.0 1249.0 286.5
[541] 1710.0 286.5 1890.0 1832.5 1490.0 330.5 1441.0 470.5 836.5 1801.5
[551] 836.5 1710.0 981.0 6.5 756.0 756.0 374.0 1390.0 883.5 566.0
[561] 1390.0 1441.0 423.5 1199.5 1199.5 1199.5 1618.0 883.5 1298.5 6.5
[571] 423.5 1154.5 182.5 374.0 707.5 132.5 566.0 1801.5 661.5 28.0
[581] 470.5 1154.5 518.5 1029.0 28.0 28.0 518.5 883.5 1801.5 1801.5
[591] 930.5 518.5 1574.5 423.5 286.5 836.5 1490.0 1758.0 1029.0 1154.5
[601] 423.5 930.5 518.5 1862.5 1029.0 470.5 1298.5 797.5 28.0 1249.0
[611] 1710.0 1199.5 237.5 661.5 1574.5 330.5 1710.0 1533.5 1490.0 1249.0
[621] 1663.0 1390.0 661.5 1663.0 1029.0 981.0 1343.0 374.0 1298.5 1710.0
[631] 1441.0 1343.0 237.5 612.5 661.5 182.5 1832.5 661.5 1154.5 132.5
[641] 836.5 182.5 1109.0 930.5 1533.5 883.5 883.5 981.0 1490.0 930.5
[651] 883.5 1109.0 1390.0 423.5 1862.5 470.5 1618.0 1343.0 286.5 470.5
[661] 930.5 1067.5 1343.0 132.5 566.0 68.0 286.5 612.5 1710.0 1298.5
[671] 286.5 182.5 28.0 1249.0 1343.0 98.0 237.5 981.0 44.5 1029.0
[681] 1441.0 930.5 286.5 1890.0 518.5 1490.0 981.0 1199.5 1663.0 566.0
[691] 286.5 1199.5 68.0 470.5 1801.5 1801.5 612.5 1862.5 836.5 1574.5
[701] 883.5 1249.0 286.5 1758.0 1490.0 981.0 566.0 423.5 1758.0 566.0
[711] 661.5 1801.5 1109.0 1298.5 1249.0 1199.5 1907.0 374.0 1067.5 797.5
[721] 286.5 1862.5 182.5 756.0 1663.0 1199.5 661.5 566.0 423.5 1154.5
[731] 612.5 1109.0 1109.0 836.5 1862.5 612.5 981.0 470.5 1390.0 374.0
[741] 518.5 797.5 1390.0 330.5 1249.0 1663.0 132.5 28.0 1758.0 756.0
[751] 1490.0 836.5 1663.0 612.5 883.5 1109.0 836.5 98.0 518.5 286.5
[761] 518.5 182.5 330.5 836.5 1249.0 1199.5 1574.5 1390.0 470.5 1710.0
[771] 981.0 518.5 1154.5 1109.0 1029.0 1574.5 1758.0 1862.5 930.5 1758.0
[781] 330.5 1710.0 981.0 182.5 1574.5 470.5 1199.5 566.0 1710.0 883.5
[791] 1533.5 883.5 237.5 1298.5 707.5 182.5 1390.0 1298.5 374.0 756.0
[801] 1441.0 182.5 286.5 470.5 1862.5 981.0 707.5 1832.5 1490.0 1441.0
[811] 836.5 374.0 930.5 1801.5 237.5 1862.5 28.0 182.5 132.5 518.5
[821] 1490.0 1249.0 1574.5 470.5 1490.0 1343.0 1199.5 286.5 836.5 1618.0
[831] 182.5 836.5 930.5 1109.0 1390.0 1109.0 1663.0 1298.5 1574.5 612.5
[841] 1758.0 1618.0 612.5 756.0 883.5 883.5 1801.5 470.5 1067.5 132.5
[851] 1618.0 707.5 1154.5 981.0 330.5 1574.5 1067.5 1918.5 286.5 44.5
[861] 132.5 1490.0 374.0 1343.0 1298.5 612.5 1249.0 1832.5 612.5 981.0
[871] 1067.5 756.0 470.5 981.0 1574.5 1154.5 1533.5 1441.0 1441.0 883.5
[881] 182.5 1758.0 1298.5 1441.0 1490.0 1029.0 1441.0 6.5 423.5 518.5
[891] 1758.0 1249.0 566.0 1298.5 1907.0 756.0 182.5 756.0 1298.5 1574.5
[901] 1801.5 930.5 883.5 797.5 1832.5 182.5 1862.5 132.5 836.5 470.5
[911] 1390.0 797.5 883.5 374.0 423.5 1533.5 1533.5 1154.5 1907.0 836.5
[921] 981.0 1710.0 1199.5 930.5 1710.0 797.5 1663.0 756.0 1390.0 1441.0
[931] 1249.0 1574.5 612.5 1441.0 1109.0 470.5 612.5 1618.0 1710.0 1390.0
[941] 1490.0 132.5 756.0 1832.5 707.5 237.5 1758.0 374.0 661.5 1067.5
[951] 797.5 1154.5 1801.5 1249.0 1758.0 1154.5 237.5 1832.5 1862.5 132.5
[961] 237.5 612.5 1862.5 1490.0 1618.0 1574.5 1710.0 836.5 182.5 1154.5
[971] 661.5 518.5 132.5 612.5 1490.0 286.5 797.5 470.5 1441.0 1663.0
[981] 1663.0 707.5 661.5 68.0 518.5 797.5 1663.0 661.5 28.0 330.5
[991] 981.0 1618.0 237.5 98.0 237.5 1390.0 330.5 1390.0 1490.0 1390.0
[1001] 566.0 1862.5 182.5 423.5 1574.5 470.5 1710.0 612.5 1390.0 756.0
[1011] 930.5 1390.0 28.0 68.0 423.5 1490.0 1199.5 28.0 1199.5 286.5
[1021] 707.5 707.5 1029.0 930.5 286.5 1199.5 1029.0 423.5 1298.5 1890.0
[1031] 1390.0 1109.0 1249.0 930.5 930.5 836.5 6.5 1618.0 1441.0 374.0
[1041] 1663.0 707.5 1249.0 981.0 1801.5 98.0 1390.0 883.5 1490.0 1154.5
[1051] 1574.5 286.5 132.5 1343.0 1574.5 1298.5 612.5 1801.5 98.0 1441.0
[1061] 1109.0 566.0 1343.0 612.5 836.5 1029.0 423.5 1154.5 1249.0 1390.0
[1071] 1907.0 1862.5 1801.5 1710.0 330.5 470.5 1801.5 98.0 1801.5 374.0
[1081] 16.5 330.5 1663.0 132.5 1490.0 1490.0 1029.0 1832.5 1574.5 707.5
[1091] 1801.5 1109.0 661.5 132.5 566.0 1109.0 423.5 470.5 1109.0 661.5
[1101] 1758.0 1029.0 1618.0 132.5 1533.5 883.5 1574.5 1890.0 44.5 1154.5
[1111] 661.5 1029.0 98.0 1029.0 374.0 566.0 566.0 182.5 286.5 661.5
[1121] 1343.0 237.5 1618.0 1249.0 836.5 132.5 797.5 1490.0 1154.5 707.5
[1131] 1574.5 1890.0 6.5 1067.5 68.0 707.5 1390.0 1758.0 423.5 423.5
[1141] 883.5 330.5 981.0 981.0 1574.5 1758.0 1390.0 330.5 930.5 1618.0
[1151] 981.0 182.5 836.5 470.5 1067.5 182.5 237.5 1154.5 182.5 518.5
[1161] 1441.0 612.5 1758.0 286.5 1343.0 836.5 1109.0 237.5 566.0 1533.5
[1171] 1441.0 1343.0 1918.5 1343.0 470.5 1441.0 1801.5 1154.5 518.5 374.0
[1181] 1441.0 1109.0 423.5 797.5 756.0 1298.5 1710.0 182.5 756.0 1199.5
[1191] 797.5 1441.0 1199.5 1710.0 1533.5 1533.5 68.0 1154.5 797.5 374.0
[1201] 423.5 1029.0 237.5 1029.0 1199.5 1154.5 707.5 1618.0 1298.5 470.5
[1211] 1533.5 1490.0 1249.0 423.5 1298.5 756.0 1758.0 286.5 1710.0 661.5
[1221] 518.5 237.5 470.5 1490.0 661.5 1533.5 1862.5 981.0 661.5 1067.5
[1231] 1390.0 182.5 1758.0 1663.0 566.0 930.5 470.5 756.0 661.5 1249.0
[1241] 1249.0 518.5 1109.0 6.5 981.0 1154.5 182.5 286.5 1890.0 1343.0
[1251] 566.0 981.0 518.5 1109.0 374.0 836.5 237.5 1758.0 1758.0 1109.0
[1261] 930.5 1663.0 612.5 330.5 68.0 330.5 1801.5 1801.5 470.5 1490.0
[1271] 182.5 1249.0 1249.0 1862.5 1710.0 707.5 612.5 1710.0 182.5 1109.0
[1281] 237.5 1574.5 1862.5 612.5 1343.0 883.5 374.0 68.0 883.5 44.5
[1291] 1154.5 1890.0 132.5 237.5 1029.0 132.5 1343.0 98.0 1758.0 1758.0
[1301] 1029.0 1390.0 1832.5 1029.0 68.0 1343.0 1067.5 756.0 836.5 132.5
[1311] 1533.5 612.5 1663.0 1343.0 1533.5 182.5 661.5 1801.5 661.5 237.5
[1321] 237.5 132.5 98.0 1862.5 28.0 883.5 1154.5 1533.5 68.0 518.5
[1331] 1801.5 1029.0 1890.0 518.5 612.5 1801.5 1441.0 797.5 423.5 470.5
[1341] 423.5 1832.5 1490.0 1758.0 98.0 330.5 1298.5 330.5 661.5 330.5
[1351] 98.0 286.5 182.5 612.5 661.5 1029.0 756.0 374.0 756.0 1343.0
[1361] 930.5 1758.0 1298.5 374.0 374.0 518.5 330.5 1918.5 237.5 707.5
[1371] 1441.0 883.5 132.5 661.5 1343.0 981.0 470.5 1490.0 182.5 1758.0
[1381] 1890.0 883.5 1862.5 1199.5 883.5 1490.0 836.5 1441.0 1067.5 612.5
[1391] 1029.0 1801.5 1199.5 182.5 1343.0 1298.5 566.0 330.5 1490.0 330.5
[1401] 1801.5 930.5 1533.5 1390.0 707.5 1029.0 16.5 374.0 566.0 797.5
[1411] 423.5 1490.0 374.0 374.0 132.5 1029.0 68.0 68.0 1890.0 1663.0
[1421] 756.0 1758.0 423.5 1249.0 1067.5 1390.0 1890.0 981.0 132.5 44.5
[1431] 756.0 182.5 1441.0 1618.0 1574.5 1343.0 1298.5 707.5 612.5 930.5
[1441] 330.5 237.5 286.5 756.0 612.5 518.5 1343.0 68.0 707.5 182.5
[1451] 1029.0 1199.5 1390.0 756.0 374.0 423.5 981.0 1574.5 1832.5 883.5
[1461] 98.0 470.5 182.5 6.5 756.0 1832.5 330.5 518.5 1298.5 470.5
[1471] 756.0 836.5 1298.5 330.5 566.0 1343.0 1067.5 883.5 1441.0 1109.0
[1481] 1390.0 68.0 423.5 1343.0 661.5 981.0 1154.5 930.5 1663.0 1663.0
[1491] 756.0 98.0 1618.0 1343.0 1298.5 1663.0 930.5 44.5 182.5 1918.5
[1501] 1199.5 566.0 981.0 1832.5 518.5 1574.5 612.5 1343.0 1029.0 1067.5
[1511] 930.5 98.0 286.5 470.5 28.0 1154.5 1441.0 1801.5 182.5 518.5
[1521] 132.5 1663.0 836.5 1390.0 182.5 518.5 1710.0 756.0 237.5 1154.5
[1531] 1199.5 374.0 661.5 756.0 1199.5 1907.0 237.5 612.5 1390.0 756.0
[1541] 566.0 1298.5 836.5 132.5 1343.0 566.0 1663.0 1533.5 1832.5 470.5
[1551] 797.5 836.5 612.5 756.0 1298.5 286.5 1249.0 930.5 707.5 44.5
[1561] 1663.0 470.5 1618.0 1109.0 286.5 1533.5 707.5 1618.0 1029.0 374.0
[1571] 756.0 1618.0 1249.0 518.5 756.0 286.5 1710.0 797.5 330.5 1029.0
[1581] 981.0 883.5 374.0 930.5 518.5 237.5 883.5 330.5 883.5 883.5
[1591] 182.5 374.0 612.5 518.5 423.5 1249.0 1618.0 1249.0 1109.0 797.5
[1601] 518.5 44.5 981.0 1758.0 1441.0 612.5 1618.0 423.5 182.5 1441.0
[1611] 1574.5 237.5 182.5 1758.0 182.5 132.5 423.5 68.0 1832.5 1298.5
[1621] 286.5 286.5 1390.0 1574.5 330.5 707.5 566.0 1832.5 1199.5 883.5
[1631] 661.5 661.5 1390.0 423.5 1109.0 661.5 1890.0 1490.0 286.5 330.5
[1641] 756.0 1199.5 1758.0 68.0 612.5 1801.5 981.0 1618.0 182.5 1199.5
[1651] 44.5 1154.5 1249.0 566.0 374.0 98.0 1343.0 286.5 44.5 182.5
[1661] 1490.0 330.5 1832.5 68.0 1533.5 756.0 612.5 1663.0 1574.5 930.5
[1671] 707.5 518.5 374.0 98.0 836.5 374.0 182.5 1109.0 1249.0 1390.0
[1681] 470.5 1862.5 566.0 1199.5 1490.0 1801.5 286.5 286.5 1618.0 1574.5
[1691] 1249.0 1029.0 930.5 930.5 1249.0 423.5 237.5 1663.0 1029.0 182.5
[1701] 44.5 1298.5 6.5 286.5 423.5 1298.5 1490.0 756.0 1710.0 1390.0
[1711] 1154.5 1109.0 286.5 518.5 981.0 1618.0 981.0 1907.0 182.5 1390.0
[1721] 1710.0 836.5 132.5 132.5 883.5 1298.5 423.5 1390.0 661.5 612.5
[1731] 1029.0 1574.5 1710.0 756.0 1533.5 374.0 930.5 612.5 1574.5 1862.5
[1741] 68.0 1029.0 1154.5 286.5 1574.5 1249.0 1907.0 1710.0 1862.5 423.5
[1751] 518.5 1533.5 518.5 1199.5 423.5 44.5 1441.0 756.0 1390.0 1029.0
[1761] 374.0 98.0 1490.0 182.5 1490.0 836.5 707.5 1249.0 661.5 1490.0
[1771] 981.0 836.5 182.5 661.5 1533.5 1067.5 1249.0 930.5 1199.5 707.5
[1781] 68.0 981.0 836.5 44.5 1533.5 423.5 182.5 1907.0 707.5 518.5
[1791] 707.5 1618.0 836.5 1832.5 1533.5 1298.5 423.5 1067.5 1710.0 1154.5
[1801] 981.0 930.5 1574.5 132.5 1533.5 1710.0 237.5 1710.0 132.5 518.5
[1811] 1574.5 1390.0 423.5 1862.5 1029.0 518.5 1710.0 374.0 1199.5 797.5
[1821] 883.5 981.0 1663.0 237.5 68.0 1801.5 661.5 1343.0 518.5 237.5
[1831] 1298.5 756.0 612.5 1441.0 756.0 1663.0 797.5 1249.0 182.5 1298.5
[1841] 237.5 518.5 981.0 423.5 237.5 612.5 1154.5 1199.5 98.0 374.0
[1851] 1663.0 1574.5 330.5 1618.0 1441.0 470.5 16.5 1490.0 1862.5 237.5
[1861] 1533.5 756.0 1441.0 1249.0 1618.0 1390.0 237.5 1862.5 707.5 68.0
[1871] 1199.5 1067.5 566.0 1533.5 1109.0 423.5 566.0 566.0 423.5 1618.0
[1881] 1710.0 661.5 330.5 1907.0 1109.0 132.5 1801.5 518.5 930.5 1710.0
[1891] 1490.0 470.5 836.5 883.5 1109.0 98.0 612.5 330.5 1343.0 1862.5
[1901] 237.5 1618.0 930.5 930.5 518.5 1441.0 1249.0 423.5 1490.0 1574.5
[1911] 374.0 1154.5 1109.0 566.0 661.5 470.5 330.5 182.5 566.0 661.5
[1921] 1758.0 1663.0Selecting subsets of a vector using logical vectors
inc <- incex$income
age <- incex$age
age.ord <- order(age)
inc[age.ord[1:10]] # income of the 10 youngest employees [1] 816 987 1303 1308 896 1020 878 989 1354 1623inc[age == 18] # income of 18 years old employees [1] 816 987 1303 1308 896 1020 878 989 1354 1623 1233 1108head(age == 18) # creates a logical vector (TRUE, FALSE) and return the first six elements[1] FALSE FALSE FALSE FALSE FALSE FALSEinc[age >= 60] # income of 60 year old or older employees [1] 953 1339 1500 1033 1194 1367 1295 1109 1053 1094 1523 1568 1123 1531 1403
[16] 1170 1124 1139 1819 1622 946 1629 1682 1747 1714 1240 1722 1273 1337 1198
[31] 1471 1499 1397 1155 1749 1532 1631 1342 1528 1693 1851 1083 1501 1572 1361
[46] 1783 1311 1690 1063 1701 1102 1742 1198 1957 1521 1514 1765 1092 1651 1763
[61] 1663 960 958 1697 1575 1520 948 1821 1106 1184 1237 1046 1093 1470 1550
[76] 1462 1919 1259 1252 1589 1227 830 1296 1532 1104 1623 1122 1634 1671 1462
[91] 1591 1637 1248 1517 1399 1356 1572 1399 1904 1086 1201 1474 1690 1157 1172
[106] 1830 1368 1302 1800 1424 1800 1861 1510 1253 1342 1013 1871 1120 1272 1456
[121] 1705 1663 1934 1584 1810 1638 1486 1607 1621 1442 1840 1704 1622 1259 1211
[136] 1817 1907 1572 1565 1438inc[age <= 30 | age >= 60] # income of 30 year old or younger, or 60 years or older employees [1] 953 1339 1184 962 940 816 1338 1039 1500 977 1191 1095 1007 1033 1268
[16] 965 1156 1355 1194 1141 1367 1295 987 950 1092 1456 1031 1109 1210 953
[31] 1053 987 1184 973 1232 951 1137 1094 954 1094 1523 1294 1280 1119 1188
[46] 1568 1123 1075 1005 1531 1403 843 985 1170 1070 1004 1062 1091 1094 979
[61] 1010 1124 1069 977 1157 1139 1819 1608 1622 1015 946 782 1376 1629 887
[76] 853 1060 1682 1624 1065 1073 1111 1104 1747 1714 1033 1276 1229 1104 1073
[91] 1006 1182 1121 1028 1616 1123 1240 804 1722 1303 1205 1273 951 1517 1234
[106] 1251 1181 1104 1645 1399 863 1337 885 1161 1198 1471 1499 1397 1155 1189
[121] 1472 942 1527 1476 888 1119 1318 1096 1365 1284 1749 941 1070 1119 955
[136] 1384 1308 994 1306 1532 1559 1361 1631 948 1316 1342 1171 1528 1693 1112
[151] 1851 1083 1099 1194 1191 1501 1572 1235 1361 896 962 1353 1020 1508 1813
[166] 1446 1053 1783 1164 858 1152 1311 1690 939 1260 1202 1063 1198 976 715
[181] 917 1041 1089 1701 920 1040 932 1102 1632 1144 1103 1256 1042 789 1049
[196] 1235 1457 1058 909 1742 1215 1181 1198 1957 1521 984 1555 1514 1765 951
[211] 1159 1092 946 1410 1651 1154 791 761 1054 948 1122 1222 1259 1763 1093
[226] 980 994 1078 1232 1044 1292 1663 960 1206 958 841 1697 824 883 1257
[241] 1263 979 1575 1663 1317 1520 1235 1183 1042 1029 948 1012 878 1120 1821
[256] 1266 1106 1184 1102 1237 1160 1557 1242 1046 1052 1093 1022 1246 1470 1476
[271] 1550 1462 1647 1460 1919 942 841 1081 1301 1475 1511 1199 1317 1528 867
[286] 1259 1635 704 876 859 1439 1052 1413 949 1563 1252 989 1301 1589 1365
[301] 955 1137 1227 859 1489 830 1296 1532 1206 1104 1013 1623 1496 887 1333
[316] 732 1122 1634 1341 817 982 1671 1289 1203 924 1181 1027 1490 1409 1462
[331] 1354 1065 1089 1033 1271 1220 1324 798 913 982 1262 1013 1591 1637 1512
[346] 1449 1080 1430 1062 1385 1287 1038 809 1680 1248 999 1623 1015 1274 1517
[361] 1055 1003 1200 1048 1137 1399 1356 1385 1572 1017 904 1399 922 1172 1267
[376] 1904 1284 1242 852 1426 1086 1254 1021 879 1201 1197 1390 1151 1060 1474
[391] 1094 1214 1690 1157 1172 1337 1032 1830 1046 1074 1487 1514 868 1579 1097
[406] 1181 1501 1194 1210 1368 1272 1272 1447 1302 1800 1424 1096 1412 1241 1800
[421] 942 1111 1177 1129 1565 892 1046 1039 1861 1558 1510 1527 1138 1362 1204
[436] 792 899 1074 1760 1176 1165 1253 922 1113 1233 1342 1460 1199 1263 1193
[451] 1133 1007 720 1013 1871 948 940 1370 1120 1281 893 1118 1153 1253 1272
[466] 1018 1568 1456 1288 794 1455 1279 911 1617 1069 1121 1501 1358 887 993
[481] 1313 1226 1154 1092 1365 1239 1481 1141 727 1705 1286 861 1381 1663 1121
[496] 1934 1200 1128 1385 1584 1235 1198 1212 1185 1423 862 1250 1377 1810 1290
[511] 948 1012 1007 1197 1638 1486 1593 937 1092 1222 1336 1141 1108 1141 895
[526] 1196 1607 921 1165 1004 1273 1334 1621 1255 1458 1442 1840 1363 994 917
[541] 1039 1373 903 772 1067 1061 1181 1113 1704 1622 1147 1457 1128 780 1079
[556] 1259 931 1007 1339 1211 1120 1217 1051 1050 1093 1039 823 1222 1192 1817
[571] 863 978 1907 1199 1305 1355 1453 1572 823 1565 1068 1164 1438 782 1075
[586] 1203 1256 1429Selecting a subset of a data frame
incex[age == 18, c('income', 'edu')] # select income and educ. level for empl. of age 18 income edu
27 816 med.
86 987 med.
337 1303 med.
474 1308 high
555 896 low
571 1020 low
891 878 med.
1040 989 low
1137 1354 high
1248 1623 high
1469 1233 med.
1708 1108 lowincex18 <- subset(incex, age == 18) # creates a subset of incex
# (only of 18y old employees)
incex18 sex age edu occ oexp income
27 f 18 med. low 0 816
86 f 18 med. med. 0 987
337 m 18 med. med. 0 1303
474 f 18 high high 0 1308
555 f 18 low low 0 896
571 m 18 low low 0 1020
891 f 18 med. low 0 878
1040 m 18 low low 2 989
1137 m 18 high med. 0 1354
1248 m 18 high high 0 1623
1469 m 18 med. low 0 1233
1708 m 18 low low 0 1108# also select variables
subset(incex, age == 18, c(age, edu, occ)) age edu occ
27 18 med. low
86 18 med. med.
337 18 med. med.
474 18 high high
555 18 low low
571 18 low low
891 18 med. low
1040 18 low low
1137 18 high med.
1248 18 high high
1469 18 med. low
1708 18 low lowsubset(incex, age == 18, age:occ) age edu occ
27 18 med. low
86 18 med. med.
337 18 med. med.
474 18 high high
555 18 low low
571 18 low low
891 18 med. low
1040 18 low low
1137 18 high med.
1248 18 high high
1469 18 med. low
1708 18 low lowAssigning values to selected cells
age[1:10] [1] 62 32 56 63 20 38 39 53 49 54age[c(3, 7)] <- 0 # assign age of 0 to 3rd and 7th observation
age[1:10] [1] 62 32 0 63 20 38 0 53 49 54age[age < 18] <- NA # assign a missing value (Not Available) to age values less than 18
age[1:10] [1] 62 32 NA 63 20 38 NA 53 49 547. Logical Operators
TRUE # TRUE[1] TRUEFALSE # FALSE[1] FALSE!TRUE # ! ... logical negation (NOT TRUE)[1] FALSE!FALSE # ! ... logical negation (NOT FALSE)[1] TRUE1 == 1 # == ... EQUAL[1] TRUE1 == 2[1] FALSE1 != 2 # != ... NOT EQUAL[1] TRUE'apple' == 'apple' # logical operations also work for character strings[1] TRUE'apple' == 'orange'[1] FALSE'apple' != 'orange'[1] TRUEc(3, 7, 8) == 7 # logical operation with vectors (elementwise)[1] FALSE TRUE FALSE7 == c(3, 7, 8)[1] FALSE TRUE FALSEc(3, 7, 8) == c(1, 3, 8)[1] FALSE FALSE TRUEc(3, 7, 8) == c(1, 3, 8, 5, 7, 3) # automatically recycles shorter vector (no warning!!!)[1] FALSE FALSE TRUE FALSE TRUE FALSEc(3, 7, 8) == c(1, 3, 8, 5, 7) # automatically recycles shorter vector (warning message)Warning in c(3, 7, 8) == c(1, 3, 8, 5, 7): longer object length is not a
multiple of shorter object length[1] FALSE FALSE TRUE FALSE TRUETRUE & TRUE # & ... logical AND[1] TRUETRUE & FALSE[1] FALSEFALSE & FALSE[1] FALSETRUE | TRUE # | ... logical OR[1] TRUETRUE | FALSE[1] TRUEFALSE | FALSE[1] FALSE1 == 1 & 'apple' == 'orange'[1] FALSE1 == 1 | 'apple' == 'orange'[1] TRUE8. Missing data
# ::::: checking for missing values (NA: not available) & selecting complete data :::::
# is.na(incex) # check for missing values "is not available (na)?"
head(is.na(incex)) sex age edu occ oexp income
1 FALSE FALSE FALSE FALSE FALSE FALSE
2 FALSE FALSE FALSE FALSE FALSE FALSE
3 FALSE FALSE FALSE FALSE FALSE FALSE
4 FALSE FALSE FALSE FALSE FALSE FALSE
5 FALSE FALSE FALSE FALSE FALSE FALSE
6 FALSE FALSE FALSE FALSE FALSE FALSEany(is.na(incex)) # check whether there are any missing values[1] FALSEsum(is.na(incex)) # how many missing values? (TRUE=1 and FALSE=0)[1] 0# EXAMPLE: data frame with NAs
x.df <- data.frame(a = c(5, 3, 9, NA, 0), b = c(NA, 8, 7, 1, 1)) # generate a data frame
x.df a b
1 5 NA
2 3 8
3 9 7
4 NA 1
5 0 1is.na(x.df) a b
[1,] FALSE TRUE
[2,] FALSE FALSE
[3,] FALSE FALSE
[4,] TRUE FALSE
[5,] FALSE FALSEany(is.na(x.df))[1] TRUEsum(is.na(x.df))[1] 2x.df.complete <- na.omit(x.df) # deletes all rows with a missing (NA)
x.df.complete a b
2 3 8
3 9 7
5 0 19. Other Data Manipulations
Change order of levels for edu & occ
summary(incex) # summary stats for each variable of a data frame sex age edu occ
Length:1922 Min. :18.00 Length:1922 Length:1922
Class :character 1st Qu.:31.00 Class :character Class :character
Mode :character Median :42.00 Mode :character Mode :character
Mean :41.69
3rd Qu.:52.00
Max. :65.00
oexp income
Min. : 0.0 Min. : 704
1st Qu.: 8.0 1st Qu.:1117
Median :19.0 Median :1304
Mean :19.5 Mean :1313
3rd Qu.:30.0 3rd Qu.:1506
Max. :48.0 Max. :2115 incex$occ <- factor(incex$occ, levels = c('low', 'med.', 'high'))
incex$edu <- factor(incex$edu, levels = c('low', 'med.', 'high'))
incex$sex <- factor(incex$sex, levels = c('m', 'f'), labels = c('male', 'female'))
summary(incex) sex age edu occ oexp
male :1069 Min. :18.00 low :811 low :595 Min. : 0.0
female: 853 1st Qu.:31.00 med.:692 med.:700 1st Qu.: 8.0
Median :42.00 high:419 high:627 Median :19.0
Mean :41.69 Mean :19.5
3rd Qu.:52.00 3rd Qu.:30.0
Max. :65.00 Max. :48.0
income
Min. : 704
1st Qu.:1117
Median :1304
Mean :1313
3rd Qu.:1506
Max. :2115 head(incex$occ)[1] low high high med. low med.
Levels: low med. highhead(incex$edu)[1] low high med. med. low med.
Levels: low med. highincex$edu >= 'med.' # does not work since no order is defined!Warning in Ops.factor(incex$edu, "med."): '>=' not meaningful for factors [1] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[25] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[49] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[73] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[97] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[121] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[145] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[169] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[193] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[217] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[241] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[265] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[289] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[313] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[337] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[361] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[385] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[409] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[433] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[457] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[481] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[505] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[529] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[553] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[577] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[601] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[625] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[649] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[673] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[697] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[721] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[745] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[769] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[793] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[817] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[841] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[865] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[889] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[913] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[937] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[961] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[985] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1009] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1033] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1057] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1081] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1105] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1129] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1153] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1177] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1201] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1225] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1249] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1273] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1297] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1321] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1345] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1369] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1393] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1417] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1441] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1465] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1489] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1513] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1537] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1561] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1585] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1609] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1633] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1657] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1681] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1705] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1729] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1753] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1777] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1801] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1825] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1849] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1873] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1897] NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA NA
[1921] NA NA# create ordered factor levels (for ordinal variables)
incex$occ <- factor(incex$occ, levels = c('low', 'med.', 'high'), ordered = T)
incex$edu <- factor(incex$edu, levels = c('low', 'med.', 'high'), ordered = T)
head(incex$occ)[1] low high high med. low med.
Levels: low < med. < highhead(incex$edu)[1] low high med. med. low med.
Levels: low < med. < highincex$edu >= 'med.' [1] FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE TRUE FALSE
[13] TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE
[25] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE FALSE
[37] FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE
[49] FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[61] TRUE TRUE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE FALSE
[73] FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[85] FALSE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE
[97] TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE
[109] FALSE TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE
[121] FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE FALSE
[133] FALSE TRUE FALSE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE
[145] FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE FALSE
[157] TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE
[169] FALSE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE FALSE
[181] TRUE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE
[193] TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE
[205] TRUE FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE FALSE
[217] FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE
[229] TRUE TRUE FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE
[241] FALSE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
[253] TRUE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[265] FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE FALSE TRUE
[277] TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE FALSE TRUE TRUE TRUE
[289] TRUE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE
[301] TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE FALSE TRUE
[313] FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE
[325] FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE
[337] TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE
[349] FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[361] TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[373] TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE
[385] TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE
[397] TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[409] FALSE TRUE FALSE FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[421] FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE FALSE
[433] TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE
[445] TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE
[457] TRUE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE
[469] TRUE FALSE TRUE FALSE TRUE FALSE TRUE FALSE TRUE FALSE TRUE TRUE
[481] FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE
[493] TRUE FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE
[505] TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE FALSE TRUE
[517] FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE
[529] FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE FALSE TRUE
[541] TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
[553] TRUE FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE
[565] TRUE TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE FALSE
[577] TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE
[589] FALSE TRUE TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE
[601] FALSE FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE
[613] TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE
[625] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE
[637] TRUE TRUE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE
[649] TRUE FALSE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE TRUE
[661] TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE
[673] TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE FALSE TRUE
[685] TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE
[697] FALSE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE
[709] FALSE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE
[721] FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[733] TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE FALSE
[745] FALSE FALSE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[757] TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE FALSE FALSE TRUE
[769] FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE FALSE
[781] TRUE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE
[793] FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE FALSE
[805] TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE TRUE
[817] FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE
[829] TRUE TRUE FALSE FALSE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE
[841] TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE
[853] FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE
[865] TRUE FALSE TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE
[877] FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE
[889] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE
[901] FALSE FALSE FALSE TRUE TRUE FALSE FALSE TRUE FALSE FALSE TRUE TRUE
[913] FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE FALSE
[925] TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE
[937] TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE TRUE
[949] FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[961] TRUE TRUE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE
[973] FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[985] FALSE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[997] FALSE FALSE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE TRUE FALSE
[1009] FALSE TRUE FALSE FALSE FALSE FALSE TRUE FALSE FALSE TRUE TRUE TRUE
[1021] TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE
[1033] FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE
[1045] FALSE TRUE TRUE FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE
[1057] TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE TRUE TRUE
[1069] FALSE FALSE FALSE FALSE FALSE TRUE TRUE FALSE FALSE FALSE TRUE TRUE
[1081] FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE TRUE FALSE
[1093] TRUE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE TRUE FALSE FALSE
[1105] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE
[1117] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[1129] TRUE FALSE TRUE FALSE TRUE FALSE FALSE FALSE TRUE TRUE FALSE FALSE
[1141] TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[1153] FALSE FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE FALSE
[1165] TRUE FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE TRUE
[1177] TRUE FALSE TRUE TRUE FALSE FALSE TRUE FALSE TRUE TRUE FALSE FALSE
[1189] FALSE TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[1201] TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[1213] TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE
[1225] TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE
[1237] TRUE TRUE TRUE FALSE FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE
[1249] TRUE TRUE FALSE TRUE TRUE FALSE FALSE TRUE TRUE FALSE FALSE FALSE
[1261] TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE
[1273] TRUE FALSE TRUE TRUE FALSE FALSE FALSE FALSE FALSE FALSE FALSE FALSE
[1285] FALSE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE
[1297] FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE TRUE
[1309] TRUE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE
[1321] TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
[1333] FALSE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[1345] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE FALSE FALSE
[1357] TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE TRUE FALSE
[1369] TRUE TRUE TRUE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE FALSE
[1381] FALSE TRUE FALSE FALSE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE
[1393] TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE
[1405] TRUE FALSE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE FALSE TRUE
[1417] TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE
[1429] TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE FALSE
[1441] TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[1453] FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE
[1465] TRUE FALSE TRUE FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE TRUE
[1477] FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE FALSE TRUE
[1489] FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE FALSE FALSE FALSE
[1501] FALSE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
[1513] TRUE FALSE TRUE TRUE TRUE FALSE TRUE FALSE FALSE FALSE TRUE TRUE
[1525] FALSE TRUE TRUE TRUE TRUE TRUE FALSE FALSE TRUE FALSE TRUE TRUE
[1537] FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE
[1549] FALSE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE FALSE FALSE
[1561] TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE FALSE
[1573] FALSE TRUE FALSE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE
[1585] TRUE FALSE FALSE TRUE TRUE FALSE TRUE FALSE FALSE FALSE FALSE TRUE
[1597] FALSE TRUE FALSE FALSE FALSE TRUE FALSE TRUE FALSE TRUE TRUE FALSE
[1609] TRUE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE
[1621] TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE TRUE TRUE
[1633] TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE
[1645] TRUE FALSE FALSE FALSE TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE
[1657] FALSE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE FALSE FALSE
[1669] TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE
[1681] TRUE TRUE TRUE FALSE FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE
[1693] TRUE TRUE TRUE TRUE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE
[1705] FALSE TRUE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE TRUE FALSE
[1717] FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE
[1729] TRUE FALSE TRUE FALSE TRUE TRUE FALSE TRUE FALSE FALSE TRUE TRUE
[1741] TRUE FALSE TRUE TRUE TRUE TRUE FALSE FALSE TRUE TRUE TRUE TRUE
[1753] TRUE TRUE FALSE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE FALSE
[1765] FALSE TRUE TRUE FALSE TRUE TRUE FALSE TRUE FALSE TRUE FALSE TRUE
[1777] TRUE FALSE TRUE FALSE TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE
[1789] FALSE FALSE FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE
[1801] TRUE FALSE TRUE TRUE FALSE TRUE TRUE TRUE FALSE FALSE FALSE FALSE
[1813] FALSE TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE FALSE FALSE FALSE
[1825] TRUE FALSE FALSE FALSE TRUE FALSE FALSE FALSE TRUE TRUE FALSE TRUE
[1837] TRUE TRUE FALSE TRUE FALSE TRUE TRUE TRUE TRUE FALSE TRUE TRUE
[1849] TRUE FALSE TRUE FALSE FALSE TRUE FALSE TRUE TRUE FALSE TRUE TRUE
[1861] FALSE TRUE TRUE TRUE FALSE FALSE FALSE TRUE FALSE TRUE TRUE TRUE
[1873] TRUE FALSE TRUE FALSE FALSE TRUE TRUE TRUE FALSE TRUE FALSE FALSE
[1885] TRUE TRUE TRUE TRUE TRUE TRUE TRUE FALSE TRUE TRUE TRUE TRUE
[1897] FALSE TRUE TRUE TRUE FALSE FALSE TRUE FALSE FALSE FALSE FALSE FALSE
[1909] FALSE TRUE TRUE TRUE TRUE TRUE FALSE TRUE FALSE FALSE TRUE TRUE
[1921] TRUE FALSEUse the transform() or within() functions
# read data again (in order to get original occ, edu and sex variables)
incex <- read.table('income_exmpl.dat', header = T, sep = "\t")
summary(incex) sex age edu occ
Length:1922 Min. :18.00 Length:1922 Length:1922
Class :character 1st Qu.:31.00 Class :character Class :character
Mode :character Median :42.00 Mode :character Mode :character
Mean :41.69
3rd Qu.:52.00
Max. :65.00
oexp income
Min. : 0.0 Min. : 704
1st Qu.: 8.0 1st Qu.:1117
Median :19.0 Median :1304
Mean :19.5 Mean :1313
3rd Qu.:30.0 3rd Qu.:1506
Max. :48.0 Max. :2115 incex <- transform(incex,
occ = factor(occ, levels = c('low', 'med.', 'high')),
edu = factor(edu, levels = c('low', 'med.', 'high')),
sex = factor(sex, levels = c('m', 'f'), labels = c('male', 'female'))
)
summary(incex) sex age edu occ oexp
male :1069 Min. :18.00 low :811 low :595 Min. : 0.0
female: 853 1st Qu.:31.00 med.:692 med.:700 1st Qu.: 8.0
Median :42.00 high:419 high:627 Median :19.0
Mean :41.69 Mean :19.5
3rd Qu.:52.00 3rd Qu.:30.0
Max. :65.00 Max. :48.0
income
Min. : 704
1st Qu.:1117
Median :1304
Mean :1313
3rd Qu.:1506
Max. :2115 # read data again (in order to get original occ, edu and sex variables)
incex <- read.table('income_exmpl.dat', header = T, sep = "\t")
summary(incex) sex age edu occ
Length:1922 Min. :18.00 Length:1922 Length:1922
Class :character 1st Qu.:31.00 Class :character Class :character
Mode :character Median :42.00 Mode :character Mode :character
Mean :41.69
3rd Qu.:52.00
Max. :65.00
oexp income
Min. : 0.0 Min. : 704
1st Qu.: 8.0 1st Qu.:1117
Median :19.0 Median :1304
Mean :19.5 Mean :1313
3rd Qu.:30.0 3rd Qu.:1506
Max. :48.0 Max. :2115 incex <- within(incex, {
occ <- factor(occ, levels = c('low', 'med.', 'high'))
edu <- factor(edu, levels = c('low', 'med.', 'high'))
sex <- factor(sex, levels = c('m', 'f'), labels = c('male', 'female'))
})
summary(incex) sex age edu occ oexp
male :1069 Min. :18.00 low :811 low :595 Min. : 0.0
female: 853 1st Qu.:31.00 med.:692 med.:700 1st Qu.: 8.0
Median :42.00 high:419 high:627 Median :19.0
Mean :41.69 Mean :19.5
3rd Qu.:52.00 3rd Qu.:30.0
Max. :65.00 Max. :48.0
income
Min. : 704
1st Qu.:1117
Median :1304
Mean :1313
3rd Qu.:1506
Max. :2115 Clean up - delete objects
objects() [1] "A" "age" "age.ord" "B"
[5] "inc" "incex" "incex18" "smpl.ind"
[9] "x" "x.df" "x.df.complete" "y" rm(x, y, age, inc, age.ord, incex18, x.df, x.df.complete)
objects()[1] "A" "B" "incex" "smpl.ind"10. Basic Computing with Data
Simple statistics for a data vector
table(incex$edu)
low med. high
811 692 419 mean(incex$age) [1] 41.68835median(incex$age)[1] 42range(incex$age)[1] 18 65quantile(incex$age) 0% 25% 50% 75% 100%
18 31 42 52 65 summary(incex$age) Min. 1st Qu. Median Mean 3rd Qu. Max.
18.00 31.00 42.00 41.69 52.00 65.00 summary(incex$edu) low med. high
811 692 419 mean(incex$income)[1] 1313.145mean(incex$income[incex$edu == 'low']) # mean for a subset[1] 1178.983tapply(incex$income, incex$edu, mean) # means by educational level low med. high
1178.983 1335.103 1536.561 tapply(incex$income, list(incex$edu, incex$occ), mean) # by education & occ. status low med. high
low 1060.534 1306.302 1503.111
med. 1110.309 1270.835 1555.839
high NA 1305.747 1600.598tapply(incex$income, list(incex$edu, incex$occ), sd) # corresp. standard dev. low med. high
low 152.3427 159.2897 124.9030
med. 145.8130 159.7552 145.8256
high NA 148.7302 171.3144Use with() or attach() and detach()
# alternatively use with() instead of repeated 'incex$"
with(incex, tapply(income, edu, mean)) low med. high
1178.983 1335.103 1536.561 with(incex, tapply(income, list(edu, occ), mean)) low med. high
low 1060.534 1306.302 1503.111
med. 1110.309 1270.835 1555.839
high NA 1305.747 1600.598# or attach() and detach()
# income # not found since "income" only exist within "incex"
attach(incex) # makes all variable of the incex data frame available
head(income)[1] 953 1224 1466 1339 1184 1196tapply(income, edu, mean) low med. high
1178.983 1335.103 1536.561 tapply(income, list(edu, occ), mean) low med. high
low 1060.534 1306.302 1503.111
med. 1110.309 1270.835 1555.839
high NA 1305.747 1600.598detach(incex) # after you are done, detach data set
# income
# !!! WARNING: in order to avoid confusions when manipulating data
# avoid using attach() and detach() !!! But attaching data is useful for plotting. 11. Writing Simple Functions
# ::::: mean value & standard dev. :::::
mean.val <- function(x)
{
# computes mean value of vector x
sum(x) / length(x)
}
mean.val # without (), prints the body of the functionfunction(x)
{
# computes mean value of vector x
sum(x) / length(x)
}mean.val(incex$income)[1] 1313.145mean(incex$income)[1] 1313.145sd.val <- function(x)
{
# computes standard deviation of vector x
sqrt(sum((x - mean.val(x))^2) / (length(x) - 1))
}
sd.val(incex$income)[1] 255.5624sd(incex$income)[1] 255.5624# define your own my.summary() function
my.summary <- function(x)
{
# returns mean, sd, n, and standard error
# x ... numeric vector (no missings allowed)
m <- mean.val(x)
s <- sd.val(x)
n <- length(x)
se <- s / sqrt(n) # standard error
c(mean = m, std.dev = s, n = n, s.e. = se)
}
my.summary(incex$income) mean std.dev n s.e.
1313.145161 255.562379 1922.000000 5.829351 12. Visualizing Data
Histogram & kernel density estimation
attach(incex) # attaches a data frame such that variables (colums)
# are directly accessible by their name
# after you no longer need the attached data frame detach() it
hist(income)
hist(income, prob = T)
lines(density(income), col = 'red') # kernel density estimate; lines() adds lines to the active plot
detach(incex) # detaches the incex data frame
library(lattice) # load "lattice"-package: more fancy histograms and density plots
# most convenient with formula method
histogram(~ income, data = incex)
histogram(~ income | sex, data = incex) # plot income by sex
histogram(~ income | sex * edu, data = incex) # plot income by sex x edu
densityplot(~ income, data = incex)
densityplot(~ income | sex, data = incex)
densityplot(~ income | sex * edu, data = incex)
Barplot
barplot(table(incex$occ), main = 'occupational status')
barplot(table(incex$edu), main = 'education')
plot(~ occ, data = incex) # alternative way
table(incex$age)
18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43
12 8 15 18 29 31 38 62 48 50 38 49 50 44 52 43 50 48 44 53 30 48 46 48 53 43
44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65
34 49 42 48 51 48 41 53 49 49 38 44 43 47 47 49 38 24 36 19 15 8 plot(occ ~ age, data = incex) # plot calls spineplot
spineplot(occ ~ age, data = incex)
cdplot(occ ~ age, data = incex) # conditional density plot
barplot(table(incex$occ, incex$edu), main = 'occupational status', xlab="edu", ylab="occ")
barplot(prop.table(table(incex$occ, incex$edu), 2), main = 'occupational status', xlab="edu", ylab="occ")
plot(occ ~ edu, data = incex)
plot(occ ~ edu + sex, data = incex) # need mouse or keyboard entry to confirm page change
mosaicplot(occ ~ edu, data = incex)
mosaicplot(edu ~ occ, data = incex)
mosaicplot(occ ~ edu + sex, data = incex)
mosaicplot(occ ~ edu + sex, data = incex, color = c('blue', 'red'))
mosaicplot(~ occ + edu + sex, data = incex) # alternative formula
Scatter Plot
plot(income ~ oexp, data = incex)
coplot(income ~ oexp | edu, data = incex)
coplot(income ~ oexp | edu * occ, data = incex)
# from the "lattice"-package
xyplot(income ~ oexp, data = incex)
xyplot(income ~ oexp | edu, data = incex)
xyplot(income ~ oexp | edu * occ, data = incex)
13. Basic Tables
sapply(incex, mean)Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
returning NA
Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
returning NA
Warning in mean.default(X[[i]], ...): argument is not numeric or logical:
returning NA sex age edu occ oexp income
NA 41.68835 NA NA 19.49792 1313.14516 sapply(incex, class) sex age edu occ oexp income
"factor" "integer" "factor" "factor" "integer" "integer" sapply(incex, function(x) sum(is.na(x))) sex age edu occ oexp income
0 0 0 0 0 0 apply(incex, 2, function(x) sum(is.na(x))) sex age edu occ oexp income
0 0 0 0 0 0 apply(incex, 1, function(x) sum(is.na(x))) 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
273 274 275 276 277 278 279 280 281 283 284 285 286 287 288 289
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
594 595 596 597 598 599 600 601 602 603 604 605 606 608 609 610
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
787 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1092 1093 1094 1095 1096 1097 1098 1100 1101 1102 1103 1104 1105 1106 1107 1108
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1284 1285
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
1926 1927
0 0 Create tables
xtabs(~ occ + edu, data = incex) # with formula method edu
occ low med. high
low 485 110 0
med. 245 364 91
high 81 218 328xtabs(~ sex, data = incex)sex
male female
1069 853 xtabs(income ~ sex, data = incex) # sum of incomesex
male female
1515297 1008568 xtabs(income ~ sex, data = incex) / xtabs( ~ sex, data = incex) # mean income by sexsex
male female
1417.490 1182.377 with(incex, tapply(income, sex, mean)) male female
1417.490 1182.377 with(incex, tapply(income, list(occ, edu), mean)) low med. high
low 1060.534 1110.309 NA
med. 1306.302 1270.835 1305.747
high 1503.111 1555.839 1600.598Compare group means
with(incex, tapply(income, sex, summary))$male
Min. 1st Qu. Median Mean 3rd Qu. Max.
772 1239 1425 1417 1584 2115
$female
Min. 1st Qu. Median Mean 3rd Qu. Max.
704 1028 1157 1182 1334 1919 with(incex, tapply(income, sex, mean)) male female
1417.490 1182.377 with(incex, tapply(income, sex, sd)) male female
232.9100 220.1769 with(incex, tapply(income, sex, sd) / sqrt(c(table(sex)))) # s.e. male female
7.123595 7.538714 boxplot(income ~ sex, data = incex, varwidth = T, horizontal = T)
boxplot(income ~ sex, data = incex, varwidth = F, horizontal = T)
t.test(income ~ sex, data = incex)
Welch Two Sample t-test
data: income by sex
t = 22.668, df = 1866, p-value < 2.2e-16
alternative hypothesis: true difference in means between group male and group female is not equal to 0
95 percent confidence interval:
214.7708 255.4546
sample estimates:
mean in group male mean in group female
1417.490 1182.377 t.test(income ~ sex, data = incex, var.equal = T)
Two Sample t-test
data: income by sex
t = 22.525, df = 1920, p-value < 2.2e-16
alternative hypothesis: true difference in means between group male and group female is not equal to 0
95 percent confidence interval:
214.6423 255.5831
sample estimates:
mean in group male mean in group female
1417.490 1182.377 Crosstables
with(incex, table(sex))sex
male female
1069 853 tab <- with(incex, table(sex, edu))
tab edu
sex low med. high
male 450 402 217
female 361 290 202plot(sex ~ edu, data = incex)
chisq.test(tab)
Pearson's Chi-squared test
data: tab
X-squared = 4.2096, df = 2, p-value = 0.1219tab <- with(incex, table(occ, edu))
tab edu
occ low med. high
low 485 110 0
med. 245 364 91
high 81 218 328plot(occ ~ edu, data = incex)
chisq.test(tab)
Pearson's Chi-squared test
data: tab
X-squared = 877, df = 4, p-value < 2.2e-16tab <- with(incex, table(occ, edu, sex))
tab, , sex = male
edu
occ low med. high
low 183 40 0
med. 186 175 33
high 81 187 184
, , sex = female
edu
occ low med. high
low 302 70 0
med. 59 189 58
high 0 31 144addmargins(tab) # add totals to table, , sex = male
edu
occ low med. high Sum
low 183 40 0 223
med. 186 175 33 394
high 81 187 184 452
Sum 450 402 217 1069
, , sex = female
edu
occ low med. high Sum
low 302 70 0 372
med. 59 189 58 306
high 0 31 144 175
Sum 361 290 202 853
, , sex = Sum
edu
occ low med. high Sum
low 485 110 0 595
med. 245 364 91 700
high 81 218 328 627
Sum 811 692 419 1922ftable(tab) # print a better formated table sex male female
occ edu
low low 183 302
med. 40 70
high 0 0
med. low 186 59
med. 175 189
high 33 58
high low 81 0
med. 187 31
high 184 144ftable(addmargins(tab)) sex male female Sum
occ edu
low low 183 302 485
med. 40 70 110
high 0 0 0
Sum 223 372 595
med. low 186 59 245
med. 175 189 364
high 33 58 91
Sum 394 306 700
high low 81 0 81
med. 187 31 218
high 184 144 328
Sum 452 175 627
Sum low 450 361 811
med. 402 290 692
high 217 202 419
Sum 1069 853 1922mosaicplot(occ ~ edu + sex, data = incex)
14. Basic Data Structures
Vectors (numeric & character)
(v <- c(3, -2, 13, 10.5))[1] 3.0 -2.0 13.0 10.5is.vector(v)[1] TRUEis.matrix(v)[1] FALSElength(v)[1] 4v[3:4][1] 13.0 10.5(v2 <- c('a', 'b', 'c', 'b'))[1] "a" "b" "c" "b"is.vector(v2)[1] TRUElength(v2)[1] 4v2[3:4][1] "c" "b"names(v) <- names(v2) <- 1:4
v 1 2 3 4
3.0 -2.0 13.0 10.5 v2 1 2 3 4
"a" "b" "c" "b" Factor
(f <- factor(c(0, 1, 1, 0)))[1] 0 1 1 0
Levels: 0 1(f <- factor(c(0, 1, 1, 0), labels = c('male', 'female')))[1] male female female male
Levels: male femaleis.factor(f)[1] TRUElength(f)[1] 4f[3:4][1] female male
Levels: male female(f2 <- as.factor(v2)) # transform a character vector into a factor1 2 3 4
a b c b
Levels: a b cMatrix
(m <- matrix(1:20, nrow = 4, ncol = 5)) [,1] [,2] [,3] [,4] [,5]
[1,] 1 5 9 13 17
[2,] 2 6 10 14 18
[3,] 3 7 11 15 19
[4,] 4 8 12 16 20is.matrix(m)[1] TRUEdim(m)[1] 4 5m[2:3, 3:4] [,1] [,2]
[1,] 10 14
[2,] 11 15dimnames(m) <- list(1:4, paste('X', 1:5, sep = ''))
m X1 X2 X3 X4 X5
1 1 5 9 13 17
2 2 6 10 14 18
3 3 7 11 15 19
4 4 8 12 16 20m[2:3, c('X3', 'X4')] X3 X4
2 10 14
3 11 15(m2 <- cbind(v, m)) # create a matrix by binding columns together v X1 X2 X3 X4 X5
1 3.0 1 5 9 13 17
2 -2.0 2 6 10 14 18
3 13.0 3 7 11 15 19
4 10.5 4 8 12 16 20is.matrix(m2)[1] TRUEis.data.frame(m2)[1] FALSE(m3 <- cbind(v, v2, f, m)) # matrix of character strings v v2 f X1 X2 X3 X4 X5
1 "3" "a" "1" "1" "5" "9" "13" "17"
2 "-2" "b" "2" "2" "6" "10" "14" "18"
3 "13" "c" "2" "3" "7" "11" "15" "19"
4 "10.5" "b" "1" "4" "8" "12" "16" "20"Data frame
(d <- data.frame(v, v2, f, m)) v v2 f X1 X2 X3 X4 X5
1 3.0 a male 1 5 9 13 17
2 -2.0 b female 2 6 10 14 18
3 13.0 c female 3 7 11 15 19
4 10.5 b male 4 8 12 16 20is.data.frame(d)[1] TRUEis.matrix(d)[1] FALSEdim(d)[1] 4 8d[2:3, c('X3', 'X4')] X3 X4
2 10 14
3 11 15d[, 'X3'] # select variable X3[1] 9 10 11 12d$X3 # alternative way to select X3[1] 9 10 11 12# m3$X3 # does not work for matrices, only works for data frames
dimnames(d) # names can be changed as for the matrix above[[1]]
[1] "1" "2" "3" "4"
[[2]]
[1] "v" "v2" "f" "X1" "X2" "X3" "X4" "X5"List
(l <- list(v, v2, f, m)) # list with four list elements[[1]]
1 2 3 4
3.0 -2.0 13.0 10.5
[[2]]
1 2 3 4
"a" "b" "c" "b"
[[3]]
[1] male female female male
Levels: male female
[[4]]
X1 X2 X3 X4 X5
1 1 5 9 13 17
2 2 6 10 14 18
3 3 7 11 15 19
4 4 8 12 16 20is.list(l)[1] TRUElength(l)[1] 4l[4] # fourth list element returned as a list of length 1 (containing a matrix)[[1]]
X1 X2 X3 X4 X5
1 1 5 9 13 17
2 2 6 10 14 18
3 3 7 11 15 19
4 4 8 12 16 20l[[4]] # fourth list element returned as matrix X1 X2 X3 X4 X5
1 1 5 9 13 17
2 2 6 10 14 18
3 3 7 11 15 19
4 4 8 12 16 20(l <- list(V1 = v, V2 = v2, sex = f, data = m)) # list with assigned names$V1
1 2 3 4
3.0 -2.0 13.0 10.5
$V2
1 2 3 4
"a" "b" "c" "b"
$sex
[1] male female female male
Levels: male female
$data
X1 X2 X3 X4 X5
1 1 5 9 13 17
2 2 6 10 14 18
3 3 7 11 15 19
4 4 8 12 16 20l$sex[1] male female female male
Levels: male female